Skip to main content

Searching In a Smarter Way

"There’s nothing on TV." You hardly hear that anymore. In the past few decades, television has exploded from a handful of channels to hundreds. The only downside is deciding what to watch.

Today’s viewers are awash in content. In addition to cable channels, there are apps from networks and sports leagues and over-the-top services like Netflix and Hulu. This has prompted a new refrain: “I can’t decide what to watch.”

The obvious solution is to improve content discovery — to make it easier for people to connect to the programs and movies they want and to watch them on whichever device is most convenient at the moment.

But that’s easier said than done. One big obstacle is that most search solutions today still return clumsy results. It’s still too hard for people to find the shows they want by searching for logical keywords like, say, the name of a cast member. They can’t key in or speak the name of their favorite star and then be directed to the latest TV episodes or movies featuring that actor.


The answer is for search-and-discovery tools to evolve from static, one-size-fits-all systems to intuitive, recommendation-based offerings.

The good news is that advances in artificial intelligence and machine learning are dramatically improving the underlying search algorithms and metadata. This means better search results, more personalized recommendations and more targeted results for viewers. TV search engines can now track and categorize viewing patterns. They know what’s trending broadly and deliver content that’s more relevant and interesting to you.

This is good news not only for viewers but also for studios, broadcasters and networks that want to fully monetize their content catalogs.

Until now their untapped back catalogs have been buried by the wild proliferation of content and distribution opportunities.

The key to more intuitive search and better discovery is real-time and regionalized metadata. By using enhanced metadata powered by AI and machine learning, entertainment providers can make their catalogs more searchable and discoverable. Ultimately, they can increase viewership by presenting more relevant content to their audiences more of the time.

The beauty of enriched metadata and linking is that it can help surface the most relevant content in real time. It provides discovery systems with a deeper knowledge of entertainment content by identifying relationships between content and keywords — such as Premier League, Manchester United andWayne Rooney — and, most important, understanding the strength or weighting of those connections. Trending data and algorithms enable more contextually relevant discovery experiences by assessing what is happening in the world at any moment to anticipate what viewers will want next.

Recently, for instance, there was a spike in interest in comedian Jordan Peele, whose satirical horror film Get Out was the highest-grossing original debut ever. A content-discovery engine fueled by machine learning can help viewers connect to the back catalog of Jordan Peele programs, including his appearances on Mad TV, his Comedy Central show, Key & Peele, and his other collaborations with comedian/actor Keegan-Michael Key.


Another aspect of TiVo’s application of AI and machine learning is the way real-time trending data is used to surface entertainment based on social media and current events. This also enables studios, networks and broadcasters to better monetize their catalogs because their discovery engines know when specific movies, TV shows or celebrities are trending and ensure the related information is current.

AI and machine learning can also enable conversational search features. Take the Wimbledon tennis tournament. Viewers should be able to search for matches simply by stating, “Find the Federer match,” for example. Even if “Wimbledon” and “tennis” are never mentioned, the system will know that Roger Federer is a tennis champion and Wimbledon is the optimal result.

When using a conversational search application, users can ask questions and follow-up queries that the technology will understand. This way a user can engage in a free-flowing dialogue with the voice system responding in the same manner as an intelligent person in a conversation.

Thanks to advancements in AI and machine learning, studios, broadcasters and networks can create better experiences for viewers. They stand to gain increased revenue — and happier customers — by providing better search, recommendation and voice-enabled discovery features.