There’s a running joke in the streaming world. By the time you decide what to watch, the snacks are over, or the mood is gone. Netflix even launched a tool called “Play Something” to end the meaningless catalog scrolling. But an inherent part of the problem is also the platform’s bad search system.
For years, users have complained about the algorithmic recommendation system’s tendency to repeat listings, while the lack of a proper sort and filter system only worsens the situation. The categories system, on the other hand, is quite overwhelming.
Thanks to AI, the search tool on Netflix could soon shed its bad reputation. According to Bloomberg, Netflix is testing an AI-powered overhaul of the search tool that will give users more freedom with their inputs in order to find films and TV shows of a certain type.
The new search engine will let users “look for shows using far more specific terms, including the subscriber’s mood, for example, the company said,” per the report. This OpenAI-powered search will also allow users to make queries that “go well beyond genres or actors’ names.”
The feature, which is opt in, is already available for some users to try in Australia and New Zealand on iOS.
Netflix spokesperson MoMo Zhou confirmed to The Verge that Bloomberg’s story is accurate. Zhou says that the test will expand to the US “in the coming weeks and months” and that there aren’t currently plans for the feature outside of iOS.
“It’s early days for the feature and we’re really in a learn and listen phase for this beta,” Zhou says.
The OpenAI-powered search engine lets customers look for shows using far more specific terms, including the subscriber’s mood, for example, the company said,” says the Bloomberg report. “It will then recommend options from the company’s catalog.
For now, the limited-scale testing of the updated search tool is limited to the iOS platform, and there is no clarity when, or if, it will expand to the web and Android client. Netflix, however, is no stranger to AI.
On the contrary, the company maintains a public dashboard of how it is implementing Machine Learning technology across its entire service stack. Search is a crucial part of those endeavors.
Why am I excited about it?
In a paper released back in 2022, the company detailed how it pays close attention to what users are clicking on and browsing at any given time. And more importantly, how much time they spend on any TV show or film.
Based on these activity patterns, the underlying search system figures out the user’s interests at a certain moment, and accordingly shows suggestions within the search bar dropdown before you even start typing in the text field.
That approach sounds fantastic, but Netflix also makes it clear that it relies heavily on its in-house recommendation system to populate what you see in the search results. In a nutshell, the algorithm has a high degree of command over the entire search, instead of letting users take the lead.
Netflix Search
Personalized recommendations on the Netflix Homepage are based on a user’s viewing habits and the behavior of similar users. These recommendations, organized for efficient browsing, enable users to discover the next great video to watch and enjoy without additional input or an explicit expression of their intents or goals.
The Netflix Search experience, on the other hand, allows users to take active control of discovering new videos by explicitly expressing their entertainment needs via search queries.
In this talk, we discuss the importance of producing search results that go beyond traditional keyword-matches to effectively satisfy users’ search needs in the Netflix entertainment setting.
Motivated by users’ various search intents, we highlight the necessity to improve Search by applying approaches that have historically powered the Homepage. Specifically, we discuss our approach to leverage recommendations in the context of Search and to effectively organize search results to provide a product experience that meaningfully adds value for our users.
This is where AI, and its natural language chops, come into the picture. Instead of limiting users to search by names or genres, and then letting them scroll past a long list, they can simply narrate their mood or viewing requirements in the search field. Imagine having a back-and-forth with an AI and finding just the right thing to watch?
So far, my interactions with AI tools such as Gemini Live have been quite rewarding, and I wish Netflix offers a similar experience with its AI-charged search tool in the near future. For now, I am hoping AI will make it easier to find what’s new and soon-to-leave on Netflix, among other granular inquiries, as well.
