We are fortunate here at The Filter – we get to focus on just personalisation for OTT/ DTV clients – nothing else. As a business we offer a managed service as many of our clients want personalisation that is (ironically) personalised for their content and customers. This means that we also get to explore with our clients many new areas of innovation that more productised services struggle to flex into. Innovation is part of what makes us get out of bed in the morning.
So here is our list of the most exciting areas of innovation that we here at The Filter have or will be soon developing.
Recommend Live TV – Lots of people assume that personalisation and recommendations are only for on-demand content. However, for many clients, Live TV is still >50% of all viewing. So surely you should include it in any ‘Recommended For You’ or ‘Most Popular’ algorithm? If you have sports and news content, this will always be best live. But how do Live TV recommendations work in your UX? Recommending the best shows for a customer to watch from the entirety of next weeks’ live viewing is clearly not a great experience. So you have to link any live recommendations to what is on now. In practice, many of our client use countdowns for shows that are about to air i.e. in the next 15 minutes. We feel this countdown experience adds to the excitement.
Personalise the Whole Page – Why should you limit personalisation to just within each rail / swim lane? If a particular user never clicks on ‘Sports For You’ rail, then this rail should be moved down the page. You need to make sure that any changes are gradual as too much variation can end up leaving users disorientated. To also build on this, you might also want to keep certain rails fixed; we find ‘Continue Watching’ and ‘`Trending’ are rails that should always stay fixed as they perform key user journey roles.
Combine Editorial and Data Science Tools – Many potential clients often assume that there is a battle between editorial teams and data science based algorithms. This should not be a debate as the sweet spot is in combining the power of both. We here at The Filter have an editors’ hero tool that allows editors to select a pool of content daily, weekly, or monthly and then the algorithms order these titles for that individual/ household. If that household never watches horror titles or sport, don’t put them in the hero slot. If they have already watched a box set, exclude it from the hero slot.
Integrated Customer Journey – The Filter already offers personalised marketing for existing customers. If you have a ‘Recommended For You’ selection of titles for a customer on the screen, it makes total sense to use the same titles in marketing coms to them; email and push notification are the best channels. However, we can take this functionality further by making the whole experience integrated. When you see the push notification for the documentary show on Canada that you want to watch and click on it, it deep dives you into the actual watch screen for that show – no more hunting around for the title you have seen in the marketing.
Behavioural Messaging – This is common in e-commerce so why not in video digital presentation? When a user starts giving you evidence of interest, start to offer them more of what they want. Examples might be when a user skips over several superhero movies, remove them in real time from the rest of the movie rails as they scroll through it; when a user stops scrolling and appears stalled, offer a pop-up of the top recommendation for them that they have not already navigated over. You can even vary the marketing messaging depending on what that customer has watched – “Welcome to the home of crime/ reality/ soaps…” This behavioural personalisation functionality starts to enter into ‘next best action’ territory whereby you can imagine upselling to customer based on their viewing history “Watch Barcelona in HD for only €5 per month” after they have just watched 4 Barcelona games in SD.
Model by Cluster – Nothing is worse for a customer than an average or poor recommendation. You only start to trust recommendations when they seem to really work for you. To get to this level of quality, you must have different data science models build for different clusters. There should be between 6 and 20 clusters in any typical service. ‘Reality’, ‘Sports’, ‘Family’, ‘Short Form’ are the usual clusters but also have clusters for people who have not returned in a while or just came in for key masthead programming ‘Game of Thrones’ cluster.
Mood Matching – This made last year’s list as it has been happening for a while. But there are still recommendation products out there that don’t look deeply enough into the metadata and just rely on genre matching. When unleashing the power of algorithm, you need to work with the richest set of data and pull out the moods and context for content. Customers tend to be in the mood for something ‘dark’ or ‘uplifting’ and operators should structure their UX experiences about these moments.
We here at The Filter love looking at the future and driving innovation with our clients. Many of the above features are already live with many of our clients. When you look at YouTube you can see a glimmer of what the future of video watching might be like. Lots of traditionalists will shudder at this vision but I suspect that YouTube have made many of those decision based on clear data upside.
About The Filter
The Filter offers personalisation of key customer touch points based on proven data science. We put the right content in front of a customer at the right time. More views mean more loyalty, lower churn, and more revenue.
The Filter prides itself on working closely with clients both during set-up and roll-out to make sure that the client’s customers are always getting optimal recommendations. We are an agency not a SaaS provider. We have a genuinely deep TV understanding which means our data science solutions work exceptionally well for your viewers. We work with you to tailor our AI to your customer experience, your audiences, and your content. All integrated effortlessly into your data ecosystem allowing you to benefit from the power of personalisation easily and quickly, developing your platform at speed.
For more information, please email email@example.com