Sep 11, 2023
Where OTT providers can create competitive advantage with recommendations
We know that often enough, OTT providers are stuck between a rock and a hard place when trying to implement technology that delivers user recommendations to drive engagement. Of the two options on the table, off-the-shelf platforms require an initial outlay and to devise custom platform deployments, specialist in-house skills are required – meaning both present their own challenges. It’s time there was a solution that meets them in the middle. What is required is a cost-effective, easy-to-use platform that has the ability to run recommendation strategies to keep viewers engaged with what’s happening on the screen.
The current conundrum
Over the past couple of years, I’ve often seen OTT providers allocate their budget carefully, particularly as the market moves towards saturation and consumers cut back on spending. While off-the-shelf solutions can provide the foundation for personalised recommendations, it doesn’t make financial sense to bring them in when they carry high capital and per subscriber costs. This leads to a poor return on investment and unwanted questions from business leaders looking for an explanation.
The next logistical step is to build a solution in-house that doesn’t require a significant outlay, but it’s unlikely the right skills exist internally to build a custom platform. But I bear good news! There is a flexible and budget-friendly solution that combines data, analytics and machine learning (ML) to deliver the most relevant recommendations to expectant viewers.
Moving towards personalisation
The answer? AWS Personalize. It’s a serverless, scalable and unique personalisation platform that doesn’t cost the earth to run, and requires little working knowledge of ML. When implemented correctly, it’s also robust and secure.
A “recommended for you” carousel on a home page, while valuable, is just the tip of the iceberg. By leveraging user interaction data effectively, users could be shown a “more like this” or “other users also watched” carousel. A viewer that’s just finished a documentary about the life and times of a prominent association football player might be interested in the career of a golf legend, for example. Previous viewing habits can help inform the journey for others with similar interests.
There’s even an opportunity to re-rank search results or lists of recommendations that have been editorially curated. Users could see something completely unique from a common search result, based on what they most want to watch. AWS Personalize was not specifically developed for video content, which while may sound like bad news, it actually means that OTT providers can benefit from personalised recommendation algorithms that have been successfully used in other markets.
If a certain item needs to be promoted, the recommender can be configured to show a certain percentage of content from a promotions category. Contextual recommendations are also becoming a reality. A user’s viewing habits, such as the device used, the time of day or where they are when the content is consumed can also help drive recommendations.
From working with the technology closely, I’m all too aware that AWS Personalize can be a little tricky to deploy due to its complexity. That’s why we suggest using our Merapar Development Kit (MDK). It can help to take the hard work out of provisioning the solution, supporting the infrastructure needed to transform and ingest data at scale – meaning providers can use as much or as little as is needed.
Testing for the best results
Testing brings the best results. Multiple recommendation models can be devised with user data to automatically adjust parameters and then push the best performer forward, helping to improve the accuracy of recommendations. It’s also important to know whether users engage with the suggestions that are put to them. Clickstream data can be sent to a corresponding analytics platform to enable providers to monitor vital KPIs.
This might include the click through rate (CTR), conversion rate of journeys that began with a recommendation click, or even the uplift in overall engagement of customers that click recommendations or watch recommended content. All of these insights can enable a constant evaluation and optimisation of recommendation services.
Achieving competitive advantage
The streaming market is witnessing new entrants on a regular basis, and differentiation has never been more important to keep users engaged as the cost-of-living crisis encourages them to question the value they’re gaining form their current subscriptions. By incorporating a number of recommendation services with the help of AWS Personalize, businesses can drive competitive advantage, all while keeping tabs on financial outgoings and avoiding a reliance on in-house expertise. Where providers face initial difficulties with putting AWS Personalize to task, Merapar is on hand to get it integrated into operations seamlessly.
Want to find out more? Check out our latest whitepaper 'How to harness the power of AWS Personalize to deliver content recommendations quickly, at scale, and with ease' Click here for more info and to download your copy now.