We concluded the event with our first annual Bitmovin Innovators Network partner awards to recognize and celebrate the amazing work of our partners who embrace the fact that the industry is “Better Together”, by creating solutions with partners that are designed to simplify customers’ video workload needs and advance the viewing experience for audiences.

I am incredibly proud to share the winners of the Bitmovin Innovators Network partner awards below, and the contributions they’ve made: 

Accenture – Global Systems Integrator of the Year:

Accenture and Bitmovin exemplify the “better together” approach through their close strategic partnership, including an ongoing collaboration with the world’s largest motorsports content owners that led to joint engagements with several of the largest sports and media brands in the world.

Broadpeak – Global ISV Partner of the Year:

Broadpeak embodies the “Better Together” spirit through its unwavering strategic collaboration with Bitmovin. This powerful partnership has yielded several key benefits. Together, they have developed solutions that integrated with Bitmovin’s encoder, player, and analytics, resulting in improved workflows for customers; created a consistent two-way communication between sales teams which has resulted in successful deals with European media brands, and joint marketing and PR initiatives at local events to strengthen their joint brand presence.

MediaKind –  Global Service Provider Partner of the Year:

MediaKind and Bitmovin have developed and maintained a robust strategic partnership that has launched sports applications for world-renowned sports leagues. These applications, including launching an app with a sports league on Apple Vision Pro that garnered rave reviews at the Apple launch event, have significantly boosted market visibility for both brands.

Microsoft Azure Marketplace – Cloud Marketplace of the Year:

Bitmovin has had unprecedented success with the Microsoft Azure Marketplace, including more than 200 new customer wins since June 2023. Azure Marketplace has quickly become Bitmovin’s largest and most successful sales channel.

Nomad Media – Americas Regional Channel Partner of the Year:

Nomad Media has deployed over 30 customers on the Bitmovin Play platform in 2023 alone as part of its Nomad Media platform. Nomad Media has also innovated on the player capabilities with dynamic multi-view capabilities. These advancements were showcased to major US clients, propelling both companies forward. This collaboration not only built a strong pipeline but also significantly boosted brand recognition in the US market.

G&L Geißendörfer & Leschinsky – EMEA Regional Channel Partner of the Year:

G&L is a proactive and committed industry partner, who has worked with Bitmovin on both successful sales and marketing initiatives. The collaboration between the two companies resulted in joint revenue, a new logo, and G&L also exhibited on the Bitmovin stand at IBC 2023 where it highlighted how the two companies’ solutions work together. Bitmovin and G&L also hosted a joint CMCD webinar together, which attracted attendees from key German broadcasters and various telecoms and content providers, and it recently published an e-commerce case study with Home Shopping Europe.

Viet Communications – APAC Regional Channel Partner of the Year

Vietcoms was the first licensee for the Bitmovin Player in the Asia Pacific region. Vietcoms was selected for its hard work and efforts in securing our impressive player business in Vietnam and developing agile operational models to meet the specific customer and TelCo business needs and technical requirements.

Once again, I’d like to give huge congratulations to all the winners. A huge thank you to everyone who attended the Bitmovin Innovators Network Partner Executive Networking Event, and to every single one of our partners who continue to embrace the spirit of “Better Together.” IBC is just around the corner, and we will have some exciting initiatives and announcements coming soon to share with you ahead of the show.

The post The Bitmovin Innovators Network “Better Together” Award Winners! appeared first on Bitmovin.

Video is integral to digital experiences. Whether end-users are scrolling through social media, binging content on their connected TV, or sweating it out to an online fitness class, streaming now plays a central role in driving online engagement. 

But building video into products and services is tough. Businesses need robust streaming infrastructure to store, encode, manage, deliver, and analyze video content. Plus, most dev teams have expertise in their company’s core competency rather than back-end video technology. 

That’s where online video platforms (OVPs), video streaming application programming interfaces (APIs), and software development kits (SDKs) come into play.

Think of OVPs as all-in-one solutions. They offer a comprehensive suite of tools to manage your entire video workflow, from ingestion to analytics. These are ideal for businesses needing a user-friendly platform with minimal development effort. But if your requirements go beyond simply uploading and sharing video content, OVPs may be a poor fit.

APIs, on the other hand, provide granular control. They act as messengers, allowing you to integrate specific video functionalities like playback, encoding, or analytics into your existing applications. APIs are perfect for developers seeking the flexibility to develop advanced applications, without having to start from scratch.

Finally, SDKs are pre-built toolkits designed for integrating specific video features into mobile and web applications. They save development time by offering all the building blocks for a specialized language or task — like deploying your HTML5 player on Roku. 

SDKs are often used in conjunction with APIs and OVPs. For this reason, it’s not always a question of OVP vs. API vs. SDK, but rather which combination of technologies is best for your business.

Acronyms abound in the alphabet soup that is video streaming. But don’t worry. In this guide to OVPs, APIs, and SDKs, we define each term and explore which option is best depending on your use case. From there, we recommend the top products in each category for business leaders and software developers alike.

Technical requirements for deploying online video

Before getting into it, let’s nail down the capabilities and features needed to integrate video into your product and look at how OVPs, APIs, and SDKs support these requirements.

Encoding and transcoding 

Encoding and transcoding are often used interchangeably, but they refer to two distinct steps. Encoding involves converting RAW video into a compressed digital format directly after the video source is captured, while transcoding employs a digital-to-digital conversion process to prepare and optimize video content for distribution to end users.

Most online video content has been both encoded and transcoded before it reaches viewers. These processes are what make it possible to deliver bulky video over the internet and ensure smooth playback across a variety of devices. 

Transcoding is a critical capability that’s supported by all major OVPs and APIs. What differs, though, is how advanced and flexible different platforms’ transcoding features are. Most OVPs take a one-size-fits-all approach. This means the video bitrate, frame rate, and other technical parameters are predefined and all streams are prepared in the same way.

APIs, however, offer more control over transcoding configurations without having to access a dashboard. This allows developers to configure encoding settings and use a variety of protocols and codecs. The process of uploading videos is also automated with APIs, whereas OVPs generally require manual uploads through the interface. Finally, some encoding solutions offer per-title encoding/transcoding capabilities. 

With per-title encoding, the settings are customized to each video. We designed the Bitmovin Per-Title Encoding solution to automatically analyze the complexity of every file and create the ideal adaptive bitrate (ABR) ladder depending on the content. This ensures high-quality viewing experiences and efficient data usage by creating dynamic bitrate ladders on a case-by-case basis. The player can then select from multiple bitrates based on network and computing resources available. 

One additional item is that you can deploy Bitmovin’s VOD and Live encoders on your infrastructure within any major cloud provider using Bitmovin’s Cloud Connect feature. This helps maintain the highest cost efficiency and use Bitmovin’s infrastructure through its managed service.

Read our Video Encoding Streaming Technology Guide to learn more.

Storage

Video accounts for the majority of the internet’s traffic. As such, it’s no surprise that CDN and storage bills make up the biggest operating expenses for OTT providers. The best way to minimize these costs is through technologies like per-title encoding, so you’ll want to consider how different components of your workflow impact one another when evaluating OVPs and APIs.

A Forrester study found that Bitmovin customers running their encoding in the cloud saw a 355% ROI over a three-year period.

Other factors to think about that impact storage costs include the anticipated volume, geographic distribution, and integration efforts. Many OVPs offer built-in storage solutions as part of their platform to simplify management. This provides a centralized storage system within the platform, but it’s difficult to tailor it to your specific storage requirements.

Streaming video APIs offer a more customizable approach to storage, including the ability to integrate with popular cloud storage providers like AWS, Microsoft Azure, and Google Cloud. This means developers can adapt the approach based on their scalability and geographic redundancy needs, and also optimize storage costs based on their existing workflows.

Distribution

Video delivery comes next, which is made possible by Content Delivery Networks (CDNs) like AWS, Akamai, Microsoft Azure, and Google Cloud Marketpalce. These networks of interconnected servers ensure efficient video distribution across the world. 

Most OVPs have multiple CDNs built-in, whereas APIs often give users the flexibility to deliver streams on their own CDN. With Bitmovin, you can do either, ensuring both customization and easy workflow configuration. 

Playback

Video players are essential components of streaming platforms, giving viewers control over what they watch, which devices they watch it on, and when the content plays. Players also tie everything together, making player control critical to the workflow.

HTML5 players can be built from scratch using an open-source option or deployed and customized using a solution like the Bitmovin Player. The same goes for deploying native players for iOS and Android. Going with a pre-built option provides access to advanced features like adaptive bitrate playback, DRM support, monetization capabilities, and interactive playback controls. 

Software development kits (SDKs) also play a major role in streamlining support for a range of devices and mobile applications by providing platform-specific integration tools. This helps organizations scale their solution and ensure a high-quality viewing experience for their audience without requiring significant development time. 

OVPs always have integrated video players as part of their platform, but they may lack the flexibility and customization required for branding or integrating unique playback features.

Read our Ultimate Guide to Video Players to learn more.

Analytics

Even the most straightforward streaming workflows have hiccups. As such, insight into video performance and quality of experience is a must. Organizations need the ability to pinpoint issues before they impact their audience, gain actionable insight into viewer behavior, and optimize resource utilization with visibility across the video streaming pipeline.

OVPs typically provide basic metrics like views, watch time, and completion rate. Some take this even further with heatmaps and click-through rates. For deeper insight, though, APIs are the way to go. 

With API access, you can gain insights into a wider range of data points, including:

• Error tracking
• Stream performance
• Advertising metrics
• Viewer demographics
• And more.

With Bitmovin’s Analytics, organizations can actively track more than 200 data points in real time and see how their streams compare to industry benchmarks. They can view performance within the Bitmovin Dashboard or utilize the Analytics API to get more granular insights which can then be pushed to major data aggregator platforms, such as Grafana, Looker Studio, AWS S3, and others for a more holistic view.

Online Video Platforms (OVPs)

Now that we’ve explored the primary requirements of video streaming — encoding and transcoding, storage, distribution, playback, and analytics — let’s dive into online video platforms (OVPs) and the best options for businesses.  

What is an OVP?

Online video platforms, or OVPs, are the prefabricated homes of video streaming. They act as turnkey solutions for managing, distributing, and monetizing online video content — eliminating the need for technical expertise or third-party integrations.

With an OVP, you get it all. The content management system (CMS), HTML5 video player for web-based devices, native players for mobile experiences (sometimes), and monetization tools are built in. This is great for businesses that want an effortless solution, but customization can be limited. It’s difficult to tailor OVPs to unique business models or existing workflows. As such, OVPs are better suited for building your business’s online presence across a dedicated channel, simple video workflows that don’t need to be fine-tuned, and hosting small content libraries on your website. 

OVP benefits

OVPs act as an all-in-one streaming platform for businesses with limited developer expertise and straightforward requirements. The benefits include:

• Turnkey solution: If you’re looking to host an online streaming event, embed content on your website, or use video for employee communications, OVPs are the quickest way to get started.
• Low cost of entry: OVPs are affordable and sometimes even free. They are also a great way to test interest among your user base before investing developer resources into building out a more comprehensive solution.

OVP cons

Because OVPs are designed for simple streaming workflows, businesses are limited to the tools and capabilities built into these platforms. This means that if you’re trying to build something specific, like an esports platform or fitness app, you’d be better off with an API. 

• Limited functionality: Advanced features and specific functionalities like low-latency streaming, VR & 360, and ad insertion are often missing from OVPs.
• Lacking control: Because OVPs control every step of the streaming workflow — including the encoding technology, CDN, and player — businesses using OVPs don’t have the same control over their infrastructure. 
• Missing insight: OVPs offer basic analytics capabilities. However, businesses requiring detailed insight into viewer behavior and stream performance would be better off with a streaming analytics API.

What to look for in an OVP

If an OVP makes sense for your business or video project, you’ll want to evaluate the following aspects of selecting a vendor:

1. Ease of use: Convenience is the name of the game with OVPs, so you’ll want to pick something with an intuitive user interface (UI). The goal is to streamline tasks like uploading, managing, and distributing video content for non-technical users.
2. Feature set: Essential features like uploading and sharing content, embedding video on your website, and the ability to stream live content should be table stakes when comparing providers. From there, in-depth analytics, the ability to customize the viewing experiences, and advanced encoding capabilities help set some OVPs apart.
3. Scalability and flexibility: If you’re planning for growth, you’ll want to choose an OVP that can scale with your business. Some OVPs offer APIs to accommodate future expansion, eliminating the need to migrate to a more flexible solution. 
4. Reliability and performance: Assess the uptime guarantees, server stability, and service level agreements of each option. Additionally, look for features like adaptive bitrate streaming, integration across multiple CDNs, and global delivery capabilities to ensure smooth playback for viewers worldwide.
5. Security measures: Content protection is key for use cases like corporate communications or streaming premium content to subscribed viewers. Encryption, access controls, and digital rights management (DRM) all help to this end.
6. Customer support: Assess the level of customer support provided by the OVP vendor, including tutorials, technical assistance, and dedicated account management. Look for a vendor that offers responsive support channels and comprehensive resources to help you maximize the capabilities of the platform.

Best OVPs for businesses

You’re likely familiar with leading brands in the OVP space. YouTube, Vimeo, and Bitmovin’s Streams are three popular examples. Here’s a look at how they compare. 

YouTube

As one of the most recognizable names in online video, YouTube needs no introduction. The platform allows users to upload, view, share, and comment on videos within its platform. Businesses can also use YouTube to embed videos on their website, but YouTube branding and advertisements make this a less-than-ideal application. Monetizing the content is also restrictive, as is content security. 

Most businesses use YouTube as a way to build their online presence rather than support their video infrastructure. For that reason, it’s often categorized as a social media channel rather than as an OVP. 

Marketers and businesses shouldn’t sleep on YouTube. However, creating video-powered products and services requires taking a different approach.

Vimeo

Vimeo offers tools for making, managing, and sharing videos. The platform lets businesses and creators host virtual events, webinars, and other marketing-focused experiences. It also provides the functionality to live stream to multiple social channels and websites simultaneously.

Vimeo offers limited monetization tools and often drives traffic to vimeo.com rather than your business’s website. That said, the platform delivers ad-free experiences and more end-user customization options than YouTube.

Marketers looking for a simple way to embed video on their website and live stream across multiple platforms may want to give Vimeo a try. But if you’re serious about building native video experiences that live entirely on your owned digital properties, you’ll want a more business-oriented OVP like Bitmovin’s Streams. 

Bitmovin’s Streams

Bitmovin’s Streams helps simplify streaming for businesses, serving as a single platform for live and on-demand encoding, CDN delivery, video playback, analytics, security, and more. As an end-to-end solution that’s built for the cloud, it eliminates the complexity of building your streaming infrastructure in-house. 

Features supported by Streams include:

• Flexible video uploading and encoding for on-demand content
• Live streaming and transcoding
• Drag-and-drop Player customization
• Simple sharing and easy-to-use embedding
• In-depth analytics
• WordPress plugin for quick integration
• Content protection with Signed URLs and domain restrictions

Streams also has a simple API for organizations looking for greater control, which brings us to the next section.

“Streams is one of our most important launches to date because it helps new media companies deliver high-quality streams to audiences simply and efficiently. New media companies typically have smaller developer teams that don’t have the time and capacity to get familiar with the complexities of video streaming. Therefore, there is a clear market need for a straightforward, low- or no-code solution like Streams that removes the complexity of video streaming to deliver content at speed and scale.

Demand for video streaming has grown at an incredible rate in recent years, all of which has been underpinned by extraordinary technological advancements. However, there now needs to be a greater focus on making innovations work in a simpler, more user-friendly way so video streaming can truly become ubiquitous, to enable everyone to build video products on the same level of quality and experience as the big names like Netflix.”

– Stefan Lederer (CEO, Bitmovin)

Video Streaming APIs

APIs, or application programming interfaces, are essential tools in every developer’s toolkit. They provide the flexibility to develop advanced apps while hiding the complexity behind the scenes. Here’s a look at the role they play in the world of audio and video streaming.

What is a video streaming API?

Video streaming APIs connect developers to streaming platforms like Bitmovin using code. Unlike traditional user interfaces (UI) found on video platforms like YouTube, APIs offer programmatic access to a wide range of features and capabilities, empowering developers to build customized streaming experiences tailored to their specific needs.

Without video APIs, businesses looking to deploy unique and innovative video applications would have to start from scratch. In this way, APIs speed things up significantly. Many developers elect to use video APIs to support a wide range of functionality for creating, customizing, and controlling video workflows. 

Some platforms that offer APIs can also be managed via a no-code UI. This is a great middle ground. While the UI might not provide the same level of control and customization, API access is available should the business need it. 

APIs impose almost no limits on the external services and functionality that you can integrate into your application while speeding up development through access to core services like encoding and playback.  

How do video APIs work?

Video APIs act as intermediaries, facilitating communication between the developer’s application and the underlying streaming infrastructure. In doing so, APIs hide the intricacies of online video distribution, letting developers focus on the products they’re building. 

Here’s what takes place behind the scenes when using a video streaming API.

1. Establishing communication: Video APIs create channels for developers to interact with the underlying video streaming platform. These channels typically operate over HTTP or HTTPS protocols, allowing for secure data transmission.
2. Authentication and authorization: Before accessing the functionalities offered by the streaming video API, developers need to authenticate themselves and obtain appropriate authorization. This is often achieved through the issuance of API keys or tokens, which verify the identity of the requesting user.
3. Requesting services and data: From there, developers can use video APIs to request various services and data from the streaming platform. This may include tasks such as uploading video content, initiating encoding or transcoding processes, retrieving playback URLs, or fetching analytics metrics.
4. Processing requests: The video API then processes these requests by interfacing with the backend infrastructure of the streaming platform. This involves executing the requested operations, such as encoding/transcoding video files into multiple formats, storing content in designated locations, or generating playback manifests.
5. Handling responses: After processing requests, video APIs generate responses containing the results of the requested operations. These responses are returned to the developers in a standard data format like JSON or XML. 
6. Monitoring and management: Video APIs often include functionalities for monitoring and managing video assets and workflows. This may involve querying the status of ongoing encoding jobs, adjusting playback settings dynamically, or accessing real-time analytics data to gain insights into viewer behavior.
7. Ensuring reliability and performance: Video APIs prioritize reliability and performance to ensure smooth and uninterrupted video streaming experiences. Mechanisms for fault tolerance, load balancing, and adaptive bitrate delivery help handle varying levels of demand and end-user bandwidth and mitigate potential disruptions.

Types of video streaming APIs

Streaming APIs are often broken out by the specific capabilities they support. As such, you may hear references to more nuanced services like a live video streaming API or video analytics API. The names are self-explanatory, but let’s touch on how they compare.

VOD encoding APIs

Video-on-demand (VOD) encoding APIs take source files and convert them into adaptive streaming formats like MPEG-DASH and HLS for adaptive bitrate delivery. They also create thumbnails, subtitles, and other metadata. But that’s not all. When using Bitmovin’s encoder, you benefit from per-title encoding capabilities, multi-codec streaming, and HDR support as well.

Capabilities to look for in a VOD encoding API:

• Multi-codec and format support
• Adaptive bitrate delivery (ABR)
• Per-title (also called content-aware) encoding
• Thumbnail and metadata generation
• Cloud-based processing
• Advanced features like DRM protection and ad insertion
• Integrations with your existing cloud storage, CMS, or analytics platforms

Live streaming APIs

Broadcasting live video online is no simple task. Unlike video-on-demand (VOD) encoding APIs, which focus on processing pre-recorded content, live streaming APIs facilitate the real-time transmission of video content to viewers as it happens. These workflows often use a contribution encoder like OBS or Videon EdgeCaster, as well as a live streaming API like Bitmovin. 

Whether broadcasting live events, webinars, or gaming streams, these APIs empower developers to deliver high-quality live video content reliably and efficiently. To keep lag at a minimum, you’ll want to find a live streaming API with support for low-latency protocols like RTMP or SRT.

Capabilities to look for in a live streaming API:

• Low-latency protocols like RTMP, SRT, and WebRTC
• Support for primary and backup inputs with automatic failovers
• Integration with popular contribution encoders like OBS, Wirecast, etc.
• Integration with interactivity tools like chat and polling
• Security and DRM
• Live recording and archiving
• Analytics and insights

“Bitmovin’s flexible and customizable technology has enabled us to solve one of our unique broadcasting challenges: to seamlessly generate a vast amount of parallel live video feeds and present them to the user in the highest quality, wherever they are in the world. 

Znipe.TV’s unique technology of broadcasting time-synchronized video stream of multiple angles sets new demand on a transcoder service, which Bitmovin delivers with their fantastic technical roadmap. To achieve the unique Znipe.TV viewing experience, we chose Bitmovin’s encoding to handle the video transcoding so that we can focus on what we do best, providing world-class entertainment for fans globally, live and on demand.”

– Erik Åkerfeldt (CEO & Co-founder, Znipe.TV)

Playback APIs

Playback APIs, also called client-side video APIs, allow developers to interact with a video player’s core functionality. This includes creating video player instances, controlling playback, or loading new sources. A video player API can also be used to monitor the state of a video player and receive notifications when certain playback events occur.

While some video player APIs differ across platforms, we designed the Bitmovin Player API’s to provide platforms with a unified development experience across Web/HTML5, Android, iOS, and Roku.

Capabilities to look for in a player API:

• Cross-platform compatibility and SDKs for different devices
• Customizable video player UI
• Advanced playback features like subtitles and playback speed control
• Adaptive bitrate support
• Offline playback support
• Integration with analytics platforms
• Security features
• Testing solutions to ensure quality playback

Analytics APIs

Video analytics APIs provide extensive customization over data architecture and how it’s presented. The Bitmovin Analytics API, for instance, allows developers to export raw datasets to cloud storage buckets and further enrich their insight with information collected by other providers. 

With analytics APIs, developers gain access to real-time monitoring and reporting capabilities. Whether the goal is to detect playback errors, identify trends, or monitor audience engagement during live events, these APIs enable timely decision-making and proactive intervention should any hiccups occur.

Capabilities to look for in an analytics API:

• Data capture across an extensive range of data points
• Real-time insights and reporting
• Data customization and export
• Integration with existing analytics platforms

Considerations when comparing video APIs

We’ve covered the capabilities needed for specific parts of the workflow, but what about general considerations that apply to all streaming APIs? Here’s a look at key considerations.

Flexible deployment

Development teams shouldn’t be retrained to specific hardware or cloud services. As such, you’ll want to look for video encoding and playback APIs that are decoupled from any underlying technology. Finding video infrastructure solutions that can be deployed anywhere prevents vendor lock-in and boosts agility.

If you’re already running applications in the cloud, then finding products that can run on your existing resources often makes sense. You’ll also gain more control over costs and commitments by finding a video streaming solution that’s available on your existing cloud providers’ marketplaces.

Bitmovin’s solutions are available on AWS Marketplace, Azure Marketplace, and Google Cloud Marketplace. We also offer the flexibility to utilize your pool of resources on Google Cloud or use our solution on Akamai Cloud.

Comprehensive functionality

Video streaming workflows have a lot of moving parts. So we’d suggest finding a video API that offers coverage across every step, from encoding to playback to analytics. It’s also imperative to assess your specific needs — such as low-latency streaming, ad insertion, and advanced UI styling — before landing on a vendor. 

Check out our extensive library of interactive demos and API examples for a peak at the functionality our platform supports.

Customization

One of the main benefits of going with a video API over an OVP is the extensive customization it will allow. This is especially important at customer touchpoints like the video player. The ability to adjust the appearance and add interactive elements to the player UI will help deliver the differentiated experience you’re aiming to build. 

That said, when speed-to-market is a priority, you don’t want to start from scratch. Finding a player API that can be tweaked without having to build the entire interface is a great middle ground.

Integration effort

The ease of integrating video capabilities into your workflow will impact your development timeline and the associated costs. Teams looking to get their services to market ASAP may be better off with a turnkey OVP than a video API. But, if the flexibility of a video API is non-negotiable, then you’ll want to find a solution with extensive developer tools. Launching cross-platform video experiences is already complex, which is why builder-centric resources are worth their weight in gold. 

Any vendor worth your investment should offer:

• Documentation
• Support for popular programming languages
• Development guides
• Code samples
• Community forums
• 24/7 technical support and SLAs
• Automated testing solutions
• Dedicated software developer kits (SDKs)

OVPs vs. streaming APIs

To wrap up the last two sections, here’s a table summarizing the key differences between OVPs and APIs:

Video streaming SDKs

An SDK is a set of software-building resources tailored to a specific platform (like Roku) or scripting language (like Python). 

What is an SDK?

An SDK, or software development kit, is a set of developer-centric tools designed for a specific hardware, operating system, or language. These pre-packaged kits are made up of libraries, APIs, documentation, and code samples — essentially everything required to make a developer’s life easier.

What is a streaming SDK?

Video streaming SDKs help businesses accomplish specific tasks, such as mobile encoding or video playback on gaming consoles. While SDKs aren’t required to support this functionality, they abstract away much of the complexity and provide developers with specialized tools catered to a need.

Common video SDK Examples

Popular streaming SDKs are tailored to address the unique requirements of different platforms and use cases. Here are some of the SDKs video engineers rely on.

Encoding SDKs

Say you’re looking to build a user-generated content (UGC) mobile app that enables users to stream live video within your platform. For this, you’d need a mobile encoding SDK to convert the raw video files into a compressed streaming format for transport over the internet. 

Technologies like Streamaxia OpenSDK and the Larix Broadcaster SDK support these capabilities by encoding live content into contribution protocols like RTMP, SRT, and RTSP.

Alternatively, imagine you’re building a fitness broadcast platform like Classpass that lets users stream on-demand workout videos. Integrating the Bitmovin API directly into your platform would ensure high-quality playback for viewers and cost-effective storage for your organization. However, implementing this into your existing technology stack could require writing and maintaining code specific to the API’s structure and functionalities. 

With encoding SDKs catering to specific languages like Java, Ruby, and Python, developers can rely on pre-written methods for interacting with the Bitmovin Player API — significantly speeding up time to market.

Bitmovin offers dedicated SDKs for the following programming languages:

• PHP
• C#
• Python
• Node.js / JavaScript
• Java
• Ruby
• Go

Video player SDKs

Consider all the devices that we stream content on today. End users demand the same experience across mobile screens, web browsers, and smart TVs. All of these environments have different requirements, though, which translates to countless hours of development time. 

Using a player SDK catered to each device alleviates this challenge. Video player SDKs make it easy to deploy your solution everywhere viewers are tuning in while ensuring flawless playback across screens. 

They do so by providing the app development tools required to embed video players into specific devices, making it simple for developers to create, control, and monitor the video player experience.

Bitmovin offers dedicated SDKs for the many devices out there, including:

• Android and Android TV SDK
• Flutter SDK
• Gaming Consoles SDK
• HTML5 Web SDK
• iOS and tvOS SDK
• React Native SDK
• Roku SDK
• Smart TV SDK

Did you know…

Deploying Bitmovin’s Player on 2 or more SDKs enables customers to reach an additional 200,000 viewers monthly. Moreover, utilizing it on both iOS and Android platforms can save over 600 hours in player maintenance annually.

Learn more.

Streaming APIs vs. video SDKs

In most cases, developers use APIs and SDKs in tandem. So when considering video encoding, player, and analytics solutions, you’ll want to find developer-centric partners like Bitmovin that provide robust APIs and SDKs, extensive documentation, Github repositories, and community forums to speed up buildout.

Here’s a summary of how APIs and SDKs compare in terms of required expertise, development effort, and customization.

Conclusion

If you’re looking to add video to your service or application, you’re going to need an OVP, API, SDK, or a combination of all three. 

Here at Bitmovin, we use YouTube as a marketing channel and the Streams UI as a tool to quickly go live and share on-demand content on our website. These OVPs are great for tasks like uploading and sharing video content.

Companies looking to build innovative video platforms need more features than an OVP can provide. There’s always the option to develop bespoke solutions in-house, but it can get expensive. Plus, time to market matters. And by selecting ready-to-use streaming solutions that integrate with your existing ecosystem, businesses can speed things up.  

APIs and SDKs provide the perfect middle ground of speed and customization. That’s why we offer developer-centric video infrastructure solutions backed by API coverage across the video workflow.  Our extensive library of streaming APIs, VOD and Live Encoders, Player SDKs, and real-time Analytics simplifies building and optimizing without constraints.

Whether you need an end-to-end video platform backed by a simple API or a combination of components (such as an HTML5 player, cloud-based encoding, live encoding, or video analytics solution), we provide the development solution required to power the future of online video. 

Find out how Bitmovin’s streaming products, APIs, and SDKs can give you a competitive edge. Start your trial today.

The post Video Platforms, Video Streaming APIs, and SDKs Explained appeared first on Bitmovin.

At a recent internal hackathon, two of Bitmovin’s software engineers, Myriam Gantner and Thomas Sablattnig, explored whether AI could be used to process the large volume of data captured by Bitmovin Analytics into concise summaries and recommendations. The project was a success and is now being developed into a feature that is now available to Bitmovin customers. Keep reading to learn more about the new Analytics AI Session Interpreter. 

Background and motivation

Bitmovin Analytics allows video developers and technicians to track, monitor and analyze their video streams in real-time. It provides insights into user behavior, video player performance and much more. While it’s a valuable companion for Bitmovin’s Encoding and Player products, it can also stand alone and be used with several open source and commercial video players. It has a dedicated dashboard for visual interpretation, but can also export data for your own custom dashboards in products like Grafana or Looker Studio. 

Bitmovin Analytics collects a ton of data about the behavior and experience your customers have when watching videos, from simple metrics like play and pause duration to more technical information like video bitrate, DRM license exchange, adaptive bitrate switching and detailed logs around errors. There is a lot of information provided for both individual viewers and overall performance, so analysis can be time-consuming and sometimes overwhelming, especially if you don’t have a lot of technical or background knowledge about the entire video streaming workflow. 

What if we could use AI to process all the data and cut through the noise and make it easier to get to the source of streaming problems sooner? Could we make the insights provided more accessible to a wider audience that didn’t have technical expertise or streaming experience? Is it possible to build an analytics AI session interpreter with existing cloud resources? These are the questions we hoped to answer with this project. Keep reading to learn more about the process and results. 

Using Google’s Vertex AI + PaLM 2 models

Google’s Vertex AI

Vertex AI is a managed machine learning (ML) platform that leverages Google Cloud’s infrastructure and tools for building and training ML models. It has AutoML capabilities for quick and easy deployment, but also supports custom training for more advanced users and workflows. It integrates with other Google Cloud services like BigQuery and Pub/Sub for end-to-end intelligent data processing and analytics AI workflows. 

PaLM 2

PaLM 2 is Google’s next generation large language model that was released mid-2023. It excels at reasoning tasks and can decompose a complex task into simpler subtasks. It understands nuances of human language better than previous models and can perform multilingual translations, even when idioms or ambiguous and figurative language are used. 

Initial results

Once the initial workflow and connections were established, the next step was to see how smart it was out of the box. We began by feeding it the analytics data from a streaming session.

The question: “Can you please analyze this video streaming session?”

The answer:

The first event is a play event, which indicates that the user has started playing the video. 

The second event is a buffering event, which indicates that the video is buffering. 

The third event is a play event, which indicates that the video has finished playing.

Not so insightful. Obviously some more work was needed to get the results we were hoping for, so we began the process of improving and fine tuning the prompt/question and the model’s parameters.  

Crafting the “perfect” question

Improving the prompt to get more insightful responses was a multi-step iterative process. We asked questions and verified the accuracy of the results, leading us toward better phrasing of questions for the best outputs. This involved more clearly defining what aspects we wanted the AI to summarize and also asking it to provide recommendations for improvements. We also provided explanations of the properties that were part of the analytics session data and added context about certain metrics, including thresholds and ideal values and ranges for specific metrics (i.e. what is considered a good video startup time). Part of this included descriptions of how these various metrics would impact the viewer experience. We also learned it was better to structure the analytics data in JSON format to make it easier for the AI to interpret.

In the end, our “perfect” question grew to ~150 lines long!

Summary, analysis, and recommend solutions

Here is an example of Analytics session data input and the more useful output we were seeing after refining the question and contextual data:

Session Data

Summarization

The user watched a live stream for 6281 seconds (1.7 hours). 

The duration of the live event is unknown. 

The video was not paused and there were no buffering events. However, there were 53 quality changes during the session. This could indicate that the network connection was unstable or that the ABR logic was not working properly. The average bitrate of the video was 2179753 bps. This is a relatively high bitrate, which could indicate that the video was of high quality.

Analysis

The video quality changed 53 times, which is a lot. This high number of quality changes in this session could be due to a number of factors. First, the network connection of the user may have been unstable, which could have caused the video to switch between different bitrates in order to maintain a smooth playback experience. Second, the ABR logic of the video player may not have been working properly, which could have also caused the video to switch between different bitrates unnecessarily. The lack of buffer events and buffer time in this session is a good sign. This means that the video did not experience any buffering issues, which would have been a major inconvenience for the user.

Recommendation

To improve the user experience, it would be helpful to investigate the cause of the quality changes. If the network connection is unstable, the user could try using a different network or connecting to a different location. If the ABR logic is set too aggressively, the user could try adjusting the settings. If the video is encoded inefficiently, the video could be re-encoded using a more efficient codec.

User-centric insights

Beyond the text analysis and recommendations, we experimented with other potential options for providing more accessible and concise summaries of viewing sessions. This included engagement, quality of service and quality of experience scores and a “5 star” system that created an aggregate of all metrics into a single rating.

JSON response with scores

{

   ‘engagement’: 7, 

   ‘qualityOfServiceScore’: 9,

   ‘qualityOfExperienceScore’: 9

}

5 star rating examples

RATING: 1

Explanation: The video session has a low rating because the buffering time is high. This could be due to a number of factors, such as a slow internet connection or a lack of available bandwidth. The session also has a high buffer event count, which indicates that the user experienced multiple buffering interruptions. This can be a very disruptive experience for users, as it can break the flow of the video and lead to frustration. Finally, the video startup time is also high, which could indicate that the video was not optimized for the user’s device. Overall, this video session has a number of issues that could negatively impact the user experience.

RATING: 5

Explanation: This session had a good video startup time and low buffering time. The quality change rate was also good. The only downside is that the user paused the video for a long time, which may have impacted their engagement with the content.

Audience-specific session analysis

Another potential option for responses is to cater the information for specific personas with a variety of technical backgrounds, objectives and motivations when it comes to analytics data. You can imagine how a software developer, operations technician, product manager and sales or finance executive might want different levels of summarization and areas of focus when it comes to playback issues and how their own goals may be impacted. Just for fun here’s an example session summary that was generated using the voice of a teenager (which may be more accurate for a teenager from the early 2000s rather than today).

“Teenager” session analysis:

“Yo, check it out. This dude watched a live stream on his phone for over an hour. That’s crazy! He must have been really into it. The video quality was pretty good, and there were no buffering issues. But then, after about 40 minutes, the video just stopped working. The dude was pissed. He tried to restart the app, but it didn’t work. He even tried to delete and reinstall the app, but that didn’t work either. So he gave up and just went to bed.

I don’t know what happened, but it’s a bummer that the video stopped working. I’m sure the dude was really enjoying it. But at least he got to watch it for a while.“

Bitmovin Analytics AI Session Interpreter available now

Since the initial hackathon project, we’ve continued fine-tuning the process while doing the background work for connecting our APIs to make the Analytics AI Session Interpreter a reality for Bitmovin Analytics customers.

We know that many companies are sensitive to having their data used by AI models, so we are ensuring:

• Customers will need to explicitly enable this feature in their dashboard. Without that permission, no data will ever be sent to AI services.
• No customer or user identifiable information will be sent to AI services.
• Only encrypted data will be sent to AI services. 
• AI services will only retain data for the time needed to generate the output.

Sign up today to get started with a free trial of Bitmovin and supercharge your data and insights with our Analytics AI Session Interpreter! 

Related resources and links

Website: Learn more about Bitmovin Analytics

Docs: How to set up Bitmovin Analytics

Guide: Using Bitmovin Analytics with Amazon IVS

Link: Google Vertex AI

Link: PaLM 2 Large Language Model

The post Supercharging Data Insights with AI for Video Analytics appeared first on Bitmovin.

In this blog, we will explore the main hurdles health and fitness video streaming platforms encounter and discuss potential solutions for each.

1. Video Encoding and Transcoding: Achieving Compatibility and Efficiency

To make content playable and support different device screen sizes and network capabilities, efficient video encoding and transcoding solutions are necessary. By not implementing a correct encoding ladder optimized for every major device, the viewing experience can be significantly limited, giving your users a bad experience and possibly forcing them to churn. This is why utilizing a strong encoding solution such as Bitmovin’s Video On-Demand (VOD) Encoder benefits you greatly by ensuring your users have a smooth and consistent viewing experience. You can optimize VOD Encoder settings for your content through Per-Title Encoding, which plays a vital role by dynamically adjusting encoding parameters for each video, maximizing quality and bandwidth efficiency. With Bitmovin’s industry-leading Per-Title algorithm, you can deliver superior video quality while reducing storage and delivery costs. 

Check out our whitepaper on Per-Title Encoding technology to learn more about the benefits of Per-Title optimization.
When it comes to live streaming, one of the primary challenges is ensuring the stability of the stream. This requires a robust internet connection and a reliable streaming solution that can minimize disruptions and buffering during live broadcasts. By leveraging a reliable encoder, such as Bitmovin’s Live Event Encoder, that supports multiple codecs like H.264, H.265 (HEVC) and VP9 and protocols like RTMP, SRT and Zixi, you can minimize the bitrate needed for playback, optimizing bandwidth usage and improving stream stability. This benefits viewers with slower internet connections, ensuring a smooth and uninterrupted streaming experience.

2. Device support, ABR streaming, and a customizable Player: Personalized Experiences for Every User

When delivering smooth and personalized streaming experiences to your users, providing broad device support, adaptive bitrate streaming, and a customizable player are essential for you and your development team. Utilizing an open-source player in this regard can be good for select device types and platforms, but it won’t be able to cover every major device in use. You can maximize your reach and engage with a larger audience by ensuring compatibility across a wide range of devices. The player must also be able to adapt to the user’s available bandwidth to guarantee they can still stream the video in the highest possible quality, which isn’t automatically built into every player option out there. Additionally, having a customizable player skin to personalize the viewing experience goes a long way with users, pushing them to engage more with the current content.

As all of these are essential functionalities, having a single video player solution that supports various platforms and devices with ABR and other capabilities helps simplify the development process and gives you more control over how users experience and engage with your content. This is where Bitmovin’s video Player stands out, as you can seamlessly deliver your health and fitness videos across web browsers, mobile devices, smart TVs, Set-top boxes, and other popular platforms while ensuring the best viewing experience. This full feature set and broad device support eliminate the need for separate player implementations and streamline your development efforts.

3. Live-to-VOD: Increasing the lifespan and expanding access to content

Health and fitness platforms often stream live workout and wellness sessions, events, and classes. Depending on the workflow, not converting these live streams into on-demand video wastes the potential value of this content, as it gives your users more video to engage with at their convenience. By utilizing a tool that enables live-to-VOD, such as the encoding solutions provided by Bitmovin, platforms can automate capturing, encoding, and storing live streams for on-demand use. This functionality helps improve user satisfaction and increase content views, while maximizing the ROI of your live stream production. It also enables them to revisit past sessions, catch up on missed classes, and follow their fitness and wellness journey at their own pace.

4. Analytics and Viewer Insights: Understanding User Engagement

Analytics and viewer insights are vital for every health and fitness platform so they can maximize user engagement and content performance. With the right insights being tracked, you and your team may be aware of performance issues, buffering problems, or other technical issues that impact the viewing experience. Furthermore, you may face challenges in understanding your user’s behavior, how they are viewing your content, and how your ads are working if you’re utilizing them within your workflow.

A comprehensive metrics offering such as Bitmovin’s Analytics is essential as it enables you to overcome these challenges. Bitmovin’s solution provides over 200 metrics and filters, real-time monitoring, and actionable insights that empower you to optimize your content strategy, address technical issues promptly, and deliver a superior streaming experience. This data-driven approach enables you to maximize user engagement, enhance customer satisfaction, and stay ahead in the competitive health and fitness streaming landscape.

5. Ease-of-use and scalability: Simplifying Development and Accommodating Growth

The last main challenge on my list is simplifying the deployment process and ensuring scalability. This is crucial for every health and fitness platform, as when implementing a video streaming solution, it’s essential to optimize the development team’s time by prioritizing ease-of-use to help streamline the integration and setup of each part within the workflow. Implementing the wrong piece can increase your encoding time, make content harder to access, and even increase buffer times on your video player if it’s too heavy. It can also force you to forego supporting new devices if technical expertise becomes an issue.

Opting for solutions that offer user-friendly interfaces, comprehensive documentation and guides for API usage, and robust support, such as Bitmovin’s Streams solution and other video streaming technology, ensures development teams aren’t breaking their backs to get up and streaming. Additionally, depending on the framework choice, such as React/React Native or Flutter, smaller teams or ones with less video streaming expertise can maximize their code usage by utilizing what they’ve deployed across the web and use it across additional platforms/device types, enabling them to support more devices and easily customize each aspect without needing to know certain frameworks.

Furthermore, scalability becomes a key consideration as the platform grows and user demand increases. The chosen video streaming solution should provide flexible scaling capabilities, such as being cloud-native, allowing the platform to accommodate a growing content library and many concurrent viewers. This guarantees the platform can seamlessly meet workflow needs and user demands, even during peak usage periods, providing a smooth, consistent, and uninterrupted viewing experience.

In Conclusion

As you can tell from the 5 main points above, health and fitness streaming platforms face unique challenges in delivering seamless experiences. Bitmovin’s solutions for video encoding, live streaming, Player, and analytics provide essential tools to overcome these challenges and help simplify and scale streaming workflows. With efficient on-demand and live encoding, broad device support with ABR and customizable player interfaces, live-to-VOD functionality, and comprehensive analytics, platforms can optimize user engagement, make development easier, and ensure exceptional streaming experiences. With Bitmovin’s technology, you can successfully navigate the complexities of video streaming workflows and deliver high-quality content to your global audience.

If you want to see how Bitmovin’s solutions can help you simplify your existing streaming process or provide an end-to-end workflow to help launch your video streaming platform, sign up for our 30-day free trial to start testing them today (No credit card required)

The post From Workouts to Wellness: Navigating the 5 Main Challenges of Health and Fitness Video Streaming Workflows appeared first on Bitmovin.

In this blog, we will explore the main challenges faced in religious video streaming workflows and discuss possible solutions for them.

1. File Storage: Local vs. The Cloud

Many religious groups lack the in-house expertise necessary to successfully manage their video content. Many maintain internal networks, which can lead to content silos, making access difficult for team members in different locations. Internal-based systems are more secure but become more costly as content libraries expand and additional hardware is needed, and this doesn’t consider if they would be using a cloud encoder/packager to make their content streamable. This is why cloud-based solutions offer a transformative way to store, manage, and share a vast array of religious video content with your team, no matter where they are located. The cloud provides scalability, ensuring the content library can grow as the organization’s offerings expand.

Cloud environments come with robust security measures to give houses of worship the ability to protect their valuable content while enabling seamless collaboration and integration with other technologies. Depending on their capabilities, they also help you efficiently convert video information into formats and resolutions suited for streaming to empower your content further. This is where cost becomes a factor, as cloud workflows help lower prices dramatically through the integrations they have readily available. Additionally, you don’t always need to have advanced technical knowledge to set it all up, as providers such as Bitmovin have focused on providing solutions that are self-service, easy to use, and can be accessed either through a dashboard UI or API library.

Live encoding workflow with Bitmovin

2. Live & On-Demand Encoding: Setting the Right Bitrate

For houses of worship, embracing live and on-demand encoding can bring significant benefits to their streaming endeavors. Encoding is essential as it compresses and reduces the size of video files or live inputs to make them easier to store/stream and take up less space or bandwidth. This differs depending on the workflow for live or on-demand content.

VOD Encoding

For hosted video files, this can be done more efficiently through advanced video compression formats such as H.264, H.265 (HEVC), VP9, and AV1. These formats maintain the quality of the file while lowering the bitrate needed to stream them, meaning less bandwidth is needed to stream the best quality video. The challenge here is that many religious organizations need to encode multiple renditions of their files to cover each device type and available bandwidth scenario. This requires more computational power and storage, which in turn increases costs dramatically. This is where Per-Title encoding is the solution.

Per-Title encoding involves an algorithm that automatically and dynamically adjusts the bitrate based on the complexity of the content being streamed. This means that simple or static scenes may have a lower bitrate, conserving bandwidth, while more complex or dynamic scenes can have a higher bitrate to maintain optimal quality. This adaptive approach ensures that viewers receive the best possible streaming experience regardless of the content’s characteristics. Per-title also helps you save substantially on costs as it minimizes the rendition and encoding effort needed. Find out more on Per-title encoding on our dedicated page.

Live Encoding

Live encoding allows real-time broadcasting of religious services, events, and sermons to remote viewers, enabling them to participate in the worship experience regardless of their physical location. It breaks down the barriers of distance, bringing a sense of community to those who cannot attend in person. However, a couple of the main challenges with live encoding are the stability of the stream and scalability. To keep remote viewers engaged, streams need to stay up and maintain the highest quality of experience for the user. This is where a reliable internet connection plays a big part, along with an encoder that supports the file formats mentioned above, as they help reduce the bitrate needed to playback the live stream. This saves bandwidth for the viewer and improves stream stability, especially for those with slower internet connections.

Live encoding workflow with Bitmovin

Additionally, costs and computational power for encoding matter for live streaming, which is why Per-Title will eventually be a major factor and one we talk about in our blog on Per-Title encoding for live streaming.

3. Device Support: Reaching a Larger Audience

The next challenge is related to video playback. The video player is essential for houses of worship as it ensures smooth playback of live or on-demand content on the platforms across every device supported. You should also be able to give users a unique experience by customizing the player interface to align with your faith or religious-based streaming service’s branding, supporting accessibility features and interactive elements for audience engagement, and integrating with analytics platforms to provide insights. There are multiple challenges to ensuring quality playback, and a couple of them are the ability to support more devices and ensure your player adapts to the user’s available bandwidth.

For a house of worship to expand its audience reach and support playback over the web, mobile, smart TVs, and other devices, software development kits are needed. While this can become a bit more technical depending on the devices you’re looking to support, the video player you’re utilizing also must have support for them, as it will help you deploy and deliver a native and seamless experience for the viewers you’re looking to engage. A video player, like Bitmovin’s Player, that covers a large number of devices, is the best solution, as it helps you get set up for the devices you want to stream on while giving you the tools to support more in the future. Additionally, to provide the best user experience while streaming content, the player must constantly monitor the viewer’s streaming environment to adapt to any sudden changes in bandwidth availability. By having the right encoded renditions of your content, your player should be able to handle this with ease.

4. User Experience: Measuring Content Quality

For religious streaming services, knowing how your viewers are engaging with your content is essential to understanding how your streams are doing. By tracking video performance metrics, user engagement, and audience behavior, you can get a complete picture of how your viewers’ experience is and improve the way your content is provided to them. When implementing analytics tools, you should be able to monitor multiple metrics, such as:

Audience metrics 

• Play attempts, 
• Unique users, 
• Concurrent users, 
• Plays per country, 
• Plays per device

Quality of experience metrics 

• Seek events
• Time of video start
• Length of video
• Bitrate
• Buffering

The challenge with video analytics is making sure you have access to the necessary dimensions that give you the specific, actionable data you need to evaluate and act on. Depending on your setup, analytics will either be included in your end-to-end platform or another tool you can integrate into your streaming workflows, such as Bitmovin’s Streams and Analytics.

In Conclusion

In sum it up, the issues that arise when streaming video to religious and faith-based organizations can be efficiently addressed with the right solutions. The cloud provides scalability, accessibility, and cost efficiency for content hosting and management. A dependable video player improves playing on a variety of devices, while live and on-demand video encoding bitrate optimization guarantees smooth streaming experiences. Understanding how an audience interacts with a video and how to improve streaming techniques is made possible by video analytics. Churches that adopt such technologies will be able to better serve their online followers, grow their communities, and reach more people.

If you want to see how Bitmovin’s solutions can help you simplify your existing streaming workflow or give you the tools to launch your video streaming platform, sign up for our 30-day free trial to start testing them today (No credit card required).

The post <strong>Faith-Based Video Streaming: 4 Major Challenges (and Solutions) for Religious Organizations   </strong>  appeared first on Bitmovin.

Event-based tracking

A good starting point is a concept that’s applicable across all variations of analytics, event-based tracking. However, GA is architected around collecting so-called “hits”. While a hit, as a generic event, is a good proxy to measure various behaviors, the GA version is far too general for online video analytics. In video, GA is able to simply measure frequencies via the first click (e.g. as a proxy for a play), but that’s not enough to measure the quality of experience (QoE) of a user – in this case, it tells you not whether the video successfully started after a user clicked play.
For video analytics, the play is only where the story begins, as video is a time-based medium. 
To get an accurate representation of video engagement it’s important for the metrics to reflect the medium. To do so, you need more than a frequency measurement – every metric that’s duration-based has to be normalized by total session/segment length. For example, a real use comparison is around video quality via bitrate expenditure, consider the following two measurable events:

1. A two-minute segment captured at 1 MBit quality
2. A 30-second segment captured at 5 Mbit quality

Google Analytics will not weigh the Mbits based on the time segments and will measure the average bitrate at 3Mbit. However, when you normalize the values according to time, the average bitrate is 1.8Mbit. If you’re looking at GA, your perception is that you have a pretty good overall quality video stream, when the reality is a completely different story. This is pretty standard for Google Analytics averages, it even applies for time spent on site.

The instrumentation challenge

Now that we’ve established the importance of tracking events correctly, we can address the next issue – types of trackable video events and their origin. Tracking video events pose an additional challenge that one shouldn’t underestimate, platform consistency. Using GA or any general Analytics tool will come with the challenge of identifying and unifying events across different platforms. Since there are thousands of different devices, applications, and players, you need to be able to expose different events to hook your metrics up to. These differences need to be accounted for at any time when instrumenting and maintaining a video analytics deployment. An industry best practice is to establish a collector approach that provides data consistency across all platforms (ex: iOS, Android, web, Roku, …).

Aggregate vs. the individual

At the next level of online video analytics, it’s absolutely critical that you have the ability to monitor individual events of specific users. This granularity enables you to derive insights and hypotheses into service improvements (without even considering error or piracy monitoring). The shortfall of GA is its inherent design towards data aggregation, instead of identifying stand-out events (like errors), GA will aggregate the data to provide a holistic view of your service.
To really improve aggregate metrics you need to be able to review the behavior of a player, session-level monitoring is essential to making smart decisions around your video service.
Bitmovin’s Video Analytics applies the session-level methodology to ensure that any video service has a clear understanding of their player’s performance, providing data around Startup Time, Video Bitrate Expenditure, Device Type, Location, Stream Type, and more!

Real-time data for real-time decisions

The final shortcoming of GA is its ability to deliver data in real-time, an especially critical feature when you’re monitoring the performance of a live stream. Depending on the trackable event, GA will deliver data up to 24 hrs after its occurrence, which isn’t at all helpful when you start hearing about platform streaming issues on your Twitter feed. GA is capable of delivering information such as impressions and clicks in near real-time, but it doesn’t compare to analytics that measures performance in real-time and provide in-depth alerts that enable quick and timely reactions to any potential issues.

What you need for online video analytics

To reiterate, Google Analytics is a great base layer of analytics, especially for web and marketing metrics, but it has its limitations outside of that, especially if you’re running an OTT platform or service. To ensure that you’re delivering a top-of-the-line QoE, I’d highly recommend launching an easy-to-implement set of video analytics that measure detailed event-based data sets, can be applied for nearly every consumer device, and does it in real-time. To find out how Bitmovin’s Online Video Analytics can supplant the shortcomings of GA check out our page here, or get in touch with one of our experts.

Video technology guides and articles

• Back to Basics: Guide to the HTML5 Video Tag 
• What is a VoD Platform?A comprehensive guide to Video on Demand (VOD)
• Video Technology [2022]: Top 5 video technology trends
• HEVC vs VP9: Modern codecs comparison
• What is the AV1 Codec?
• Video Compression: Encoding Definition and Adaptive Bitrate
• What is adaptive bitrate streaming
• MP4 vs MKV: Battle of the Video Formats
• AVOD vs SVOD; the “fall” of SVOD and Rise of AVOD & TVOD (Video Tech Trends)
• MPEG-DASH (Dynamic Adaptive Streaming over HTTP)
• Container Formats: The 4 most common container formats and why they matter to you.
• Quality of Experience (QoE) in Video Technology [2022 Guide]

The post Why Google Analytics are not suitable for Online Video Analytics appeared first on Bitmovin.

There is one constant that has emerged from the chaos that was 2020, that despite how many new streaming services emerged and how many consumers purchased new devices to view the plethora of new content, every single one of these new (and existing services) experienced countless video errors. Errors in streaming are nothing particularly new, nor will they entirely disappear for the foreseeable future, as the nature of internet streaming is steeped with various issues that need debugging or more often than not, based on problems that may be outside of the control or influence of video services.

Technical video errors come in all shapes, colors, and values

Much like all web-based services and/or pages, and regardless of the back-end Video Player(s) that an organization uses to power their service or platform, video errors are always displayed using an error code that typically comes with a specific error message (ex: 404 – “Page not found”). However, the level of detail that derives from the code and message is very dependent on the documentation that comes with any commercial, native, or open-source player. All video streaming error messages can be sorted into one of three categories:

1. Clear – The error and message point to a specific and identifiable error behavior.
2. Ambiguous – Often indicated with a “catch-all” message, these error types can be attributed to many different types of error behavior. Although error origin is provided, there is no specific or identifiable behavior(s) subsumed under that error.
3. Unclear – As the name suggests, these video errors are completely uninformative and often read as “Unknown”, “Null”, or something similar.

An analysis of the Bitmovin Analytics database indicated that the distribution of error messages and codes were broken down as follows:

It’s important to note that some of the categorizations can be debated based on other contributing factors. Even so, the most striking takeaway is that 20% of errors are identified as “unclear”. Unclear errors are often the most costly to resolve as they cannot be debugged by simply looking at the message and code, and will need significant engineering or solutions manpower to resolve. Even the best Video Player documentation will not help. Given the severity and volume of the unclear category, it will be the primary value when calculating the cost of video errors and the potential monetary savings that would result from properly identifying unclear errors.

The cost of errors for video streaming

Effects on subscription video streaming (SVOD)

In a recent study and article, streaming service Vimeo released the following numbers that define the different reasons for subscriber churn for SVOD OTT services.

These results are based on a multiple-selection survey, and therefore add up to more than 100%. However, as each statement is treated as an “and” response, selections such as “technical reasons” are considered churn rate for the purposes of this paper’s calculations. Given that the other reasons are based on cost and/or content, therefore, the assumption is that errors (or technical reasons) attribute towards 6% of the churn rate. 
According to the same report from Vimeo, the average revenue per user (ARPU) across all SVOD service types is ~$15. 
*LTV = Lifetime Value
So, with an ARPU of $15, and an assumptive $15 subscription price/service the calculated customer lifetime value (LTV) with a 6% churn rate is $250 or 500 days. The next logical step is to determine how to increase the average customers’ LTV. According to the Bitmovin Analytics industry insights benchmarking data, OTT providers are experiencing a 6.6% error rate across their services. 
Based on data points from the “best-in-class” SVOD services using the Bitmovin dashboard, an individual subscriber (or household) attempts 150 plays/month, resulting in 0.33 errors per day. Over an average consumer’s service lifetime, this adds up to an error acceptance threshold of 165 errors over the period of 500 days.

In a perfect world, if a streaming service could remove 10% of their “unclear” or “ambiguous” errors with more accurate information the customer lifetime would increase by 5 days or 1.1%. In monetary terms: By reducing errors by 10% for an SVOD service with 1M subscribers and a $15/month subscription fee, the 5 days increased in lifetime value for the technical churner segment would result in an estimated revenue increase of $160,000.

Effects on ad-based video streaming (AVOD)

Given that there is a full set of additional elements within an advertising-supported video platform to support ad insertions and content protection – there are different error types that come into play, thus a different error calculation model is necessary. The AVOD cost of error model is based on research from S. Shunmuga Krishnan and Ramesh K. Sitaraman who found that viewers that experienced any interruptions to their streaming service were 2.32% less likely to revisit the video platform than a viewer who did not experience interruptions. This additional data point is especially important for AVOD services that depend on maximizing viewership, and thus the number of ads served, through driving regular consumption of their content.
Based on the Bitmovin Analytics platform for AVOD services, 25-50% of users visit the site or service weekly (recurring users), and each unique user generates around 1.5 plays per week, and AVOD platforms serve around 2 ads/play. At the time of this whitepaper’s publication, the price per 1000 ad plays (CPM) for premium content was around $60 and had an upward trend in price in upscale markets such as Germany. In the scenario where a service maintains a 30% recurring viewership and stands to lose ad revenue from 2.32% unique viewers that experience start or in-stream failures, the service would incur a cost of $1.25 per 1000 errors.

Applied at scale and applying the 6.6% error rate from Bitmovin Analytics industry insights for a service experiencing 25M play attempts per week, this error rate would result in an estimated revenue loss of $3,445/week. Unfortunately, removing all errors is not a likely scenario, however, but in this case, reducing the error percentage by 20% already results in a $35,000 revenue increase.
It’s important to note that costs for both SVOD and AVOD errors are highly variable based on the input values (subscription fee, error rate, subscriber count, etc). To find out the potential monetary impact of reducing errors for your specific use case, please visit our calculator at the following link: https://bitmovin.com/demos/cost-of-errors
Find out how to tackle these unknown video errors and to save this information for future use, fill out the form below to receive our complete “Cost of Errors: How to reduce churn with granular data in video analytics” whitepaper.

Video technology guides and articles

• Back to Basics: Guide to the HTML5 Video Tag 
• What is a VoD Platform?A comprehensive guide to Video on Demand (VOD)
• Video Technology [2022]: Top 5 video technology trends
• HEVC vs VP9: Modern codecs comparison
• What is the AV1 Codec?
• Video Compression: Encoding Definition and Adaptive Bitrate
• What is adaptive bitrate streaming
• MP4 vs MKV: Battle of the Video Formats
• AVOD vs SVOD; the “fall” of SVOD and Rise of AVOD & TVOD (Video Tech Trends)
• MPEG-DASH (Dynamic Adaptive Streaming over HTTP)
• Container Formats: The 4 most common container formats and why they matter to you.
• Quality of Experience (QoE) in Video Technology [2022 Guide]

The post Calculating the Monetary Impact of Video Errors in SVoD and AVoD Services appeared first on Bitmovin.

In the first two parts of this series on using Bitmovin’s Per-Title Encoding on AWS, we’ve focused on the architecture of the application and setting up encoding using Bitmovin Cloud Connect. But now that we have our encoded videos saved to Amazon S3, what’s next? In this part, I’ll complete the circle by introducing Bitmovin’s Video Player and Video Analytics products. I’ll explain how these two tools work together, and how to use them to gather data on user interaction with your content and measure quality of service. Finally, I’ll walk you through the setup that we used in our 2020 Bitmovin + AWS Hackathon to demonstrate the cost savings and performance of per-title encoding.

Why Do Video Analytics Matter?

Understanding how your content performs is important for a few reasons. First, detailed analytics can help you improve your quality of service as in the case of Telekom Slovenjie:

“As a customer might call in, an agent could check the types of streams the user watched, which errors they were having and on which device, and would distinguish if the error is detected on a hardline or on the actual network. With the simple analytics collector and API implementation, Telekom Slovenjiie was able to reduce their support tickets by roughly 30 percent.”

Not all video analytics providers offer as much granularity as Bitmovin. One of the big advantages of using a dedicated service for your video analytics is that you don’t have to know exactly what metrics you want to track in advance. At Bitmovin, we record over forty metrics.
The Bitmovin dashboard is the easiest way to have a first look at your data. It breaks it down into 3 areas:

• Audience shows you how people are engaging with your content. Metrics like number of plays, unique users, ISP, location, and view time are all available here.

• Quality of Service tells you more about the user experience of your videos, which includes data like start time, bandwidth used, bitrate, etc.
• Advertising is a must-have if you rely on advertising to fund your content, with metrics such as click-through rates, successful ad plays, and relative ad spot performance.

The Bitmovin Video Player

Getting this much data from users who are streaming your videos requires to be deeply embedded in the playback sessions and therefore in the players themselves. That’s where the Bitmovin Video Player comes in.
Not only does the Bitmovin Video Player provide the widest device support for playing your videos with efficient adaptive algorithms, including with multiple codecs, and allows you to dynamically insert ads into those streams, all through a rich universal yet configurable UI, but it also contains an event-based engine that will push that rich data to the Bitmovin Analytics solution to give you that fine-grained, accurate insight into how users are watching your videos.

Proof through Video Analytics

In the first and second parts of this blog series, in which we described the architecture and implementation of our application, we touched only briefly on the differences between a workflow that generates a static ladder and one that generated a ladder optimized with the Per-Title algorithm. That’s because those differences are small, and didn’t have a material impact on the implementation.
However, it is time to bring this back to the front. We are setting out to prove that Per-Title gives you significant savings when used in your production workflow, without impacting the playback experience. We can only do this through actual comparisons between different outputs encoded from the same assets.
There are usually two main ways in which Per-Title encoding delivers operational savings: reduced storage costs and reduced bandwidth costs.
The difference in storage costs is easy to calculate directly from the output of the encoding. Simply look at the difference in the total file size generated for the two encodings. The ratio between those will give you a simple and generally reliable answer. You can look at the files themselves on your Output bucket, or query the Bitmovin platform to retrieve the encoding’s statistics. Since Per-Title will behave differently with different assets, it is best to take the average across a few representative assets into consideration for this calculation. 
For bandwidth savings, it gets a bit more complicated. You could obviously look at the difference in bitrate between renditions in your 2 ladders, but there are a few complicating factors: the ladders will have a different number of renditions and different bitrates between them. And in reality, nobody streams all the renditions of your ladder at the same time. What renditions are actually played very much depends on your audience, what bandwidth they have available, what device they are playing on, etc.  You can try and model this playback usage, but at the end of the day, there is no better data than real data. Enter the Bitmovin Analytics…

What metrics should we use for this?  We are obviously looking at the quality of service here, and the data we are after is captured by two main metrics: 

• Data Downloaded which shows the amount of video data downloaded during playback sessions by users.
• Video Bitrate shows the average played bitrate across all plays on the platform. We expect to see this one is reduced by the use of Per-Title

Whilst we are at it, there are probably a few other metrics that we may want to consider keeping an eye on when evaluating how Per-Title ladders behave:

• Video Startup Time: a Per-Title ladder should not cause the startup time to increase

• Rebuffering: A Per-Title ladder will usually contain fewer renditions than a static one. This should not be to the detriment of the playback session

• Scale Factor, which is a numeric indicator of the relationship between the playback window size and the resolution your stream was delivered at. Most of the time Per-Title will allow users to stream higher resolutions at similar or lower bitrates compared to a fixed ladder, and therefore users will more often and more quickly get to watch the video that matches their player’s native resolution and stay at that level throughout the streaming session. We should therefore see this number get closer to 1 for the content encoded with Per-Title.

The best way to perform this comparison is to use an A/B test scenario. A/B tests are usually used to test the performance of different CDNs, or test the stickiness of different marketing videos. Here we will pitch static ladders against Per-Title ladders. 
Luckily, Bitmovin Analytics is perfectly suited to do A/B testing through experiments

Implementation

But before we get there, let’s complete our discussion of the implementation that will give us that information. In the previous two parts of this series, you saw how to use AWS Lambda to save video metadata and playback URLs to DynamoDB. In this section, I’ll walk you through the steps you need to add the Bitmovin Video Player and Video Analytics solutions to your application.

Embedding and Configuring the Bitmovin Web Player

We’ll create a very simple HTML page and embed the Bitmovin Web player into it.
First you will need to retrieve your Bitmovin Video Player license via the dashboard, and configure it to be allowed on your domain. 
To embed the video player, simply add the Bitmovin Player JavaScript library to the `<head>` section of your HTML file:

Next, add a `<div>` that will contain the instance of your player, and use the following JavaScript snippet to instantiate the player with your license key:

This adds an instance of the Bitmovin Player to your page. Now you need to populate it with some video data.

Passing Video Data Into the Video Player

If you’re emulating the AWS-based architecture in the previous section, you need to retrieve the video metadata saved to DynamoDB first. DynamoDB has a JavaScript API, so depending on how you want to query it, your code for retrieving records could look something like this:

In our Demo application we were loading 2 players side by side, allowing the user to select an asset from a dropdown. We were retrieving all data for our small list of assets through a `dynamodb.scan()` operation. For a more realistic application, you will probably want to query data for a single asset instead through a `dynamodb.query()` call, and then use a random (or controlled) way of selecting playback information for the Per-Title or static ladder.
Note also that you’ll probably want to find a less insecure way of enabling access to your DynamoDB. The AWS documentation has good recommendations on this subject
Once the relevant video data has been extracted, the `configure_player_with_data` function creates a properly formatted `source` payload with the URLs to the DASH and HLS manifests, and passes it to the `player.load()` method:

Integrating Analytics and Tagging Your Experiment

While the video player above works fine, we still need to connect it to our Bitmovin Analytics account to get the data flowing. This can all simply be done by modifying the `playerConfig` variable from earlier.

We then set some of the asset metadata in the `source`, allowing us to later easily identify videos in the Dashboard or analytics data. This is also where we configure our A/B experiment by simply defining an `experimentName`, and setting its value to “static” or “per-title” based on the type of ladder selected.

We can now let our users lose on our video player page and collect some data. Some will get a per-title ladder, others a static ladder. Let the data flow!

Looking at the data

After running a few experiments, we can look at the results in the Bitmovin dashboard, by going to Analytics > Quality of Service > Comparison > Experiments.
This multi-column view allows you to compare key metrics side by side for your named experiments. In our simple scenario, we only have 2 columns. Other metrics that are not displayed in this view can still be accessed in their respective dashboard view and can be broken down by experiment. 

Although we only got a very limited sample of data from this hackathon, we could already see some important trends:

• Video startup time seems actually lower with the per-title ladder. This may not be significant but is certainly good news.
• Buffering is also slightly reduced with our per-title ladder.
• The average bitrate across playback sessions is very significantly lower with per-title, with a reduction of 65% in bandwidth. _Note that the colors for that metric are incorrectly set at the time of writing. A lower value is evidently better, assuming that the level of visual quality delivered is at least similar_ 
• Data downloaded is naturally significantly lower too.
• Scale factor was not significantly different, however, but that can be attributed to the fact that our playback sessions were probably all in favorable conditions that saw all players able to quickly jump to the top rendition, which has the same resolution in both ladders. 

Another interesting comparison between the two ladders, assuming both ladders had had a good number of views, would have been to use the video bitrate heatmap to compare how the two ladders performed in terms of bitrate usage over the duration of the videos and showed much more efficient use of the reduced number of renditions.
There was unfortunately not enough time during our 2020 hackathon to conduct a more realistic experiment. If we had, the data would have been more accurate, and likely would have shown a slightly reduced bitrate saving, but without putting into question the clear advantages of using Per-Title. 

Conclusion

In part one, you saw an example of a high-level AWS architecture you can use to perform Bitmovin’s Per-Title Encodings in your own AWS infrastructure. In part two, you learned how to implement and deploy the main parts of the workflow with AWS Lambda code and DynamoDB. Finally, in this part, you saw how to add the Bitmovin Player and Analytics to run experiments comparing Per-Title and Standard encoding ladders.
Analytics are an important part of the video streaming pipeline. Whether you use Cloud Connect or Bitmovin’s managed API, you’ve seen in this post how all three of Bitmovin’s products work together to improve the video delivery and streaming experience.
Now that you have a complete picture of what’s possible using Bitmovin, let us know how we can help. Reach out to Bitmovin’s team so we can help you get started with an efficient, scalable video streaming pipeline today.

The post Cloud-based Per-Title Encoding Workflows (with AWS) – Part 3: Adding the Player and Video Analytics appeared first on Bitmovin.

Actionable insights for reactive users

Across all walks of life and varieties of business, teams, or individuals, humans can be categorized into two types of people – proactive or reactive. I found that these categories are just as applicable for Analytics vendors through discussions with my product peers for Analytics-oriented tools. Much like their general worker counter-parts proactive analytics users actively dig into their data sets to find actionable insights and improvement potential to their workflows or performance. Whereas reactive users only react to specific triggers to investigate issues, such as customer tickets, reports, and/or inquiries from other sources. And in the case of Analytics tools, from specific alerts or notifications within a given analytics tool.
After a quick review of Bitmovin Analytics, I came to the realization that our dashboard was biased towards proactive users and thus a large group of users was missing out on the benefits of the insights we provide to their service. Each metric that we provide has its own dedicated screen with a variety of filters and breakdowns that would encourage proactive users to dig into the data that best suits their needs. However, we recognized that these insights should be applied at a much broader scale and that an alarm or notification should occur whenever an issue or action to improve a user’s video platform is an essential feature to our Analytics tool. In the end, regardless of your proactive or reactive nature, we want you to sleep well at night knowing that any issues will automatically be flagged so that you don’t need to stay up all night monitoring your platform to catching any issues before they hit Twitter.

Threshold-based alerts

After some additional considerations, I also realized that a single alert-type may not be the best solution for all, as the whole proactive vs reactive user-type is more of a spectrum than a binary category. To address the spectrum of video analytics users, I had our engineering team craft threshold-based alerts. Because, let’s be honest, even the most proactive users don’t mind having an alert or two to let them know that there’s an addressable issue, instead of compulsively seeking them out. So, what do threshold-based alerts even mean?

• Sample Size –  Following the proactive vs reactive spectrum “tend to the fires that matter” approach, we added a minimum sample size which depending on the importance of the issues (or a users’ need to proactively check performance). For those who want to be notified of every possible fire, you’ll likely want to set a subjectively low sample size. Contrarily, you don’t need to stress out knowing that an issue is only affecting a small fraction of your viewer-base
• Persistence Time – The “let the baby cry it out” approach, allows users to set a minimum persistence time so that an alert fires if the problem persists for a certain period…or not if you think it’s just crying for attention
• Recovery time – The “nursing a serious injury” approach, allows users to users to set a minimum recovery time threshold, defining the duration for which the affected metric value has to remain below a specific threshold for the incident to be considered resolved

All of these configurations will ensure that regardless of your position on the proactive vs reactive spectrum, you can rest easy knowing that there won’t be any fires to put out that you missed during the day or couldn’t find during your data deep-dive. All these configurations can be made either by using the Bitmovin Analytics dashboard or the with API.
Although this all sounds very straightforward, the true art of setting up your perfect notification cycle lies in refining the alerts to match your technical and business definitions so that you don’t miss critical issues on your platform, all while not overwhelming your technical teams. 

Visibility is key – a webhook based approach

Obviously, alerts have zero value if not one sees them, even if they are set with the perfect thresholds. Hence after consulting our customer base, we decided to take these alerts one step further and integrated them into those tools where most users can see them, in messaging platforms such as MS Teams or Slack. In addition to the custom alerts, we also offer a dedicated webhook for both market-leading chats.

The post Video Analytics Alerts: Impactful business notifications for reactive individuals appeared first on Bitmovin.

Granular Data vs. Low Granularity in Video Analytics

Delivering video with standard HTTP servers means companies can use readily available web infrastructure to host and distribute video, which also means common web tools like Google Analytics can provide some insight into how a user interacts with video. However, there are limits to the insights these tools can give you.
Google Analytics is designed to treat website visits as discrete events to track the user across multiple pages—it’s not exactly suited to monitor the stream-based architecture that web video has become. It can’t provide insights like how long a video was watched or what bit rate was delivered at a specific time.
Data analytics tools that specialize in video, like Bitmovin’s, are designed to analyze streaming video on a per request level. This grants you a significantly deeper level of insight into how customers interact with content. With granular data in analytics, you don’t have to know the metrics you need in advance or build custom triggers that handle different players. Instead, you’ll receive relevant, comprehensive metrics without needing to devote developer resources.

These per-request insights help you understand every aspect of how clients interact with your content, such as subtitle usage, muting, what devices video is being served to, even when users pause and resume playback. While larger companies may be able to build pipelines that generate codecs for every possible device and frame rate, those with more limited resources have to prioritize. Granular video consumption data is vital for choosing how to allocate your resources.

The Cost of Errors

A huge benefit of granular data for video analytics is gaining insight into users who experience an error after beginning a video. Vimeo found that about 6 percent of client churn on their platform resulted from users experiencing a technical error. Errors are a fact of life when streaming video, regularly affecting more than 5 percent of desktop devices.

These errors also have high costs, especially when they can’t be properly tracked, monitored, and attributed. A 2013 study by Krishnan and Sitaraman found that “a viewer who experienced failure is 2.32% less likely to revisit the same site within a week.” In a review of Bitmovin’s customer database, Product Manager, Christoph Prager found that there are three categories of error types: Ambiguous, Unclear, and Clear.

“… clear error is when an error message and an error code, point a developer directly to an underlying issue. Whereas our definition of an ambiguous error is when an error message and error code points towards a problem area, and unclear errors are where an error code and/or message did not provide any insights into the root cause of the problem or error.” 

And according to the database, accounting for 65% of all errors, the most costly error type is thus the Ambiguous Error category. Fortunately, Bitmovin analytics track errors, and you can use their error cost calculator to see exactly how much these issues are costing you. Using Bitmovin analytics, you can more easily prioritize and fix problems, reducing the number of clients turned away from your content by technical errors and retaining them as loyal customers.

Using Granular Data for Resource Efficiency

Think of streaming video analytics as an ever-present helping hand when it comes to making quick resource management decisions. For example, if your servers hit capacity during a live event, timely and actionable analytics can mean the difference between cost-effective, appropriate scaling and losing a viewer who steps away during an interruption.
Of course, there are many dimensions of video analytics that you can choose to track. The Bitmovin analytics platform, for example, offers the ability to track over forty discrete metrics. But let’s highlight a few that are particularly crucial to business success.

Improving Viewer Experience

The biggest overall goal of video analytics is understanding and predicting how customers interact with your content. Granular data analysis allows you to start making reasonable assumptions about when and how people will interact with your content in the future. Efficiently applied, that data can help you manage client expectations and establish an auditable and improvable record of service.
This is particularly important any time you’re providing live support for customers experiencing video issues. You may have to immediately assess a client’s network connection, or how long they’ve been watching a video. Bitmovin’s real-time video analytics platform can reduce the time your customer service team spends trying to get to the bottom of how your video is being consumed by the customer. 
Remember not everything that affects your customers is under your control. Supplemental services, like video management (eg, DRM) and advertisement management, can impact customer experience. Analytics can be particularly important in these instances because knowledge from such data is essential for managing your relationship with two stakeholders: your customer and your advertising partner. Monitoring the effect these adjacent services have on your clients helps you ensure the support they provide is positively affecting customers.
In addition to helping you understand where customers turn away from content, analytics can help you feed clients relevant content to keep them engaged. Granular data helps ensure you’ll recommend videos customers watch start to finish rather than pushing them to videos that get interactions, but might not hold their attention.

Reducing Costs

One of the side effects of streaming video data is the increased importance of having the server as close to the customer as possible. As a result, video providers rely extensively on content delivery networks (CDNs). These services charge for data transferred, and video can represent a large portion of these bandwidth costs. Analyzing information like device fragmentation can enable you to directly target your user base while making efficient use of cloud-based CDNs.
Keeping track of data like video startup time, client resolution, and percentage of time spent buffering can help you contextualize network costs, develop a cheap and efficient architecture, direct development efforts, and prevent customer churn. Flagging video quality and load time issues can prevent encoding bottlenecks before they happen. Bitmovin provides a bitrate heatmap to help understand and quantify exactly how your clients consume bandwidth. With this information, you can determine how to manage server capacity during high-traffic events, or inform a choice about adopting 4K or 8K video.
Analytics can help your organization look forward and plan for future requirements. As more infrastructure is hosted in cloud services, transactions incur incremental per second and per-byte costs. Optimizing services that provide discrete amounts of data millions of times over (like video) can save significant amounts of money. Analytics give you the tools to make those decisions wisely. 

Investing in the Right Tools and Resources

If you’re prioritizing high-definition video that’s mostly consumed while users are on their phones outside the house, granular analytics will guide you to solutions like implementing codecs such as HEVC, which focuses on transmitting better quality data using smaller network connections.
Pay attention to how many users are downloading high-quality, super-fast video and how much device fragmentation affects your user block, and then apply that knowledge to weighing the stakes of investing in modern encoding innovations, like per-title encoding, multi-codec streaming, and per-scene adaptation. You can also determine what your most popular content is, then optimize the delivery of exclusively that content by providing additional encodings, targeting new users with your best material.

Getting the Most Value Out of Your Data

In a nutshell, granular video analytics allow you to efficiently make decisions about how to manage the costs and effects of your video delivery infrastructure. If you provide video as a service or rely on video to convey critical content, consider integrating Bitmovin analytics. Ensure your clients aren’t turned away by technical issues and be secure in the knowledge that you’re making informed decisions about preparing and delivering your content.
Start by signing up for a free trial period with Bitmovin to get a sense of the type of analytics available to you in the constantly evolving field of video content delivery.
Did you enjoy this post? Check out some of our other great content below:

• [Blog post] Top 5 Video Technology Trends 2021: The Future of Streaming is Around Retaining Attention
• [Blog post] Why Video Analytics & Collectors are a Must Have

The post Mitigating the Cost of Errors with Granular Data for Video Analytics appeared first on Bitmovin.