Extreme Content Personalization and AI

Every year more and more video platforms appear increasing competition in the entertainment and OTT industry as well as the demand and expectations from the users of these platforms. Content services must adapt to meet these demands more effectively and efficiently if they want to improve UX.

What better way to do this than by making content personalization for your audience?

10 MUST-HAVE features a recommendation engine should provide

Recommendations have become a tipping point for any video service’s strategy to succeed. Without the capability of recommending the right content at the right time to your users, their experience on your platform suffers, their engagement decreases, and churn increases, thus plateauing your growth. In the end, subscribers’ fatigue in OTT services is one of the main reasons for subscribers to leave your video services.

In this blog, we will explain what features and metrics a recommendation engine must have to be successful.

What is a Recommendation Engine?

A recommendation engine is an essential part of a streaming service. Their objective is to help subscribers find the right movie, show, or program at the right moment, in the right place. Ultimately, it is a tool to retain users on your platform, reducing their time to find the content.

Powered by Artificial Intelligence and combined with the knowledge and expertise on recommendation engines of your content editorial team,  you can get the most from your content catalog by delivering personalized entertainment experiences to your audience.

Must-Have Features and Metrics for your OTT Recommendation Strategy

AI-Based features

  • Contextual Recommendation: Individualized recommendations per subscriber depending on the context of the user (time of day, device, or day of the week, among others).
  • Because You Watch: Based on similarity index between different items from your content catalogue by using its content metadata, audio and video intrinsic characteristics, tags, etc.
  • Cold-Start Recommendations: Location-based recommendations, content popularity, and basic demographic data for users that just joined your video service.

Editorial tools

  • Editorial Recommendation: Weight given to a specific category to prioritize among others (i.e., your platform’s own content).
  • Blacklist: A list of content excluded from the content recommendation pool.
  • Next Episode of a Series: Incentivization to binge-watch more content from the same series.
  • Trending Now: Content trending in your region, device, timeframe, among others.
  • New Releases: Recently-released content.
  • Continue Watching: Content that you had already started watching.
  • Watch Again: Content you watched that might be interesting for you to re-watch.

Why is it important to analyze your recommendation’s performance?

Any solution or strategy implementation has no meaning if their results aren’t analysed. Knowing how recommendations are performing helps you understand if they are working properly and how to optimize them, if your user’s experience is being positively impacted by them, and, finally, if it was worth the investment.

That’s why at JUMP Data-Driven Video, we provide to our JUMP Personalizer’s customers a set of insights called Personalizer Performance to understand if their recommendation strategy is performing in the front-end apps, and what percentage of the audience it reaches, monthly. There, we look at 5 metrics to measure the functionality of our JUMP Personalizer.

Personalizer Reach

It is used to measure the percentage of users the recommendation engine has reached on the platform, meaning those who have watched at least a singular content that has been recommended to them.

Personalizer Cumulative Audience

This indicates the number of users that have watched at least a singular content that has been recommended to them.

Playback Session Viewing Time

This is the median number of minutes of recommended content that users have watched in contrast to the median number of minutes of not-recommended content that users have watched.

Personalizer Consumption Lift

Refers to the number of hours on content consumption that has increased due to the fact of having recommended content on the platform.

If you want to learn more on JUMP Personalizer or the metrics used to analyze your recommendation, click here to schedule a Free Content Personalization Workshop with our experts at JUMP, or click below to learn more on personalization.

‘Stan’s Scoop’ – Technology Partnerships are the Key to Success

IABM research clearly shows that end-users more and more are partnering with suppliers to both transform their offerings and keep on the forward moving side of the technology curve. This also goes for suppler to supplier partnering, although this has been the status quo for decades within our industry.

Looking deeper into partnerships, some thought-provoking points turned up that should be considered by vendors and end-users when partnerships get initiated due to technology.

My first point is there are too many technologies. While developing the IABM Technology and Trends Roadmap, it was clear that the more detail one got into, the deeper the “technology hole” was. This was due to a combination of multiple options from different vendors and also, by far, too much detail to be appreciated.

It was also curious to note that some bleeding edge technologies were searching for a home within our industry. Certainly from my days of being a design engineer, I constantly met with the semi-conductor companies of all sizes to learn what they had on their drawing boards and which products had availability. When seeing something really cool, the next step was find a cool application. This is precisely where the business side had to come in because using technology for technology’s sake simply puts companies out of business. Transforming technology into a real need is key. On the other hand this is exactly where innovation comes in. More often than not two road-blocks appeared: Sales department stating that isn’t what the market wants, and Product Portfolio Managers stating that a cooler product will kill their lucrative existing product sales. By having some forward looking end-users as partners, these road-blocks could be broken by getting additional thoughts and ideas as well as even some pre-orders.

This simple example stated above is more about a single product or service rather than a deeper relationship that many end-users are seeking out currently which leads me to my second point: Technology changes too quickly. Being too early or too late on the technology adoption curve without a clear, deep understanding of the technology is a clear indicator of failure. Again the solution is partnering with experts with the appropriate know-how in the field. Even when you have some in-house capability, partnering often is the speediest way to move forward. The trick here is to assure that your in-house team has buy-in and rather than fighting with the partner, they are open and sharing viewpoints, and mutually agreeing on a path forward.

I look at a technology partnership as a strategy that must be equitable on both sides. Usually groups partner because they have a business need and share a passion for innovation. This is not to say that selecting a partner is simple or falls under the security blanket of success. The facts are that the “right partner” is more often the best way to get there quickly, because the “Build, Partner, or Buy” decision can be based on time along with core business strategy.

My last point is interoperability, which begs the question to be asked: does working with a single partner mean the door is closed to having a second-source? With today’s supply chain concerns, second sources and interoperability should be priority. Often bleeding edge technologies have no immediate second source, so if this is the case, identifying this concern up-front with the partner will help to stimulate back-up options. It doesn’t mean a custom solution won’t be interoperable, as the best way to achieve interoperability is for end-users to demand interoperability.

I have only begun to scratch the surface on partnerships, and to be successful in our current world of constantly changing trends and technologies it becomes all about speed (time to market) and reliability (must provide a respectable user experience). So my point is we aren’t alone in this dog-eat-dog world of technology, we simply need to work together to be successful and strong partnerships are one way to achieve this.

Pixistor tech sheet

pixstor goes beyond storage, offering the consistency, performance and scale that teams in data intensive environments need to stay competitive

A complete shared storage solution, purpose-built for demanding media requirements, offering guaranteed performance from disk to desktop. pixstor is a data-aware scale-out NAS platform that ensures your data is always available, precisely when and where you need it, so your teams can be more productive.

We’ve developed pixstor to support the entire media lifecycle from ingest and creation through to distribution and archive, providing significant benefits for the full spectrum of media-centric organisations. pixstor can overcome your data-hungry workflow challenges.

Passion Pictures scales intelligently into the cloud to manage data on a job-by-job basis

Lockdown drove demand in Cloud-working and high-end animation. For creative production group, Passion Pictures, keeping up with the pace of this growth meant more teams collaborating using Cloud-based services as opposed to using their on-premise facilities.

Passion Pictures needed to scale into the Cloud efficiently yet intelligently, controlling all of the resources they were using; from workstations, to render compute and even data movement.

In this customer case study, find out how Passion Pictures were able to transform their data movement and production capability by scaling intelligently into the Cloud.

Pixit Media Founders Ben Leaver and Barry Evans Discuss Working With Jellyfish Pictures

No studio is an island, and as Jellyfish Pictures celebrate their 20th anniversary they talk to some of their key partners that have helped thier growth and innovation. Our founders, Barry Evans and Ben Leaver reminisce the early days of the relationship and how both companies have evolved over the years.

If you want to learn more about how pixitmedia have helped Jellyfish Pictures’ build a complete virtual studio, then you read our case study at:

https://bit.ly/3kF40qC

Pixit Media Case Study: Passion Pictures

Passion Pictures scales intelligently into the cloud to manage data and compute power on a job-by-job basis

Animation production companies and studios have found a rare spot of sunshine as the rest of the entertainment industry slowly emerges from the dreary-looking environment of the last two years.

It is a sector where visual effects artists, animators and video editors can work entirely from home and all their efforts come together online for the final result. With production workflows that are smoother to run and less risky than live-action film production, streaming providers like Disney Plus, HBO Max and Netflix are doubling down by commissioning new animated series which will provide thousands of hours of new content for subscribers.