Posts Tagged ‘Amazon Instant Video’

Amazon Fires Up Fire TV Featuring Voice Search And Content Viewing Prediction Capabilities

retAmazon today unveiled its Fire TV streaming video device. During the announcement event in Manhattan, company vice president Peter Larsen called the $99 set top box “tiny, incredibly powerful and unbelievably simple.” For users, that power and simplicity are designed to be evident in features such as the device’s ability to project and preload the content users will want to see and to navigate via voice search.

A statement by Amazon founder and CEO Jeff Bezos reads that, “Our exclusive new ASAP (Advanced Streaming and Prediction) feature predicts the shows you’ll want to watch and gets them ready to stream instantly.” Movies or tv shows are buffered for playback before users hit the play button, the company says; those choices are made by analyzing users’ watch lists and recommendations. As users’ viewing habits change, the caching prediction algorithm will adjust accordingly, and personalization capabilities should get better over time as buyers use the Fire TV device.

Read more

Amazon Gets An Emmy, But Semantic Discovery Wins Too

Yosi Glick, co-Founder and CEO of semantic taste engine Jinni, recently wrote a post about the technology and engineering Emmy award that is to be given to Amazon’s Instant Video  for its personalized recommendation algorithms.

The basis for awarding the honor, he writes, lies with Amazon’s early item-to-item collaborative filtering (CF) algorithms that analyze consumer data to find statistical connections between items and then uses that as the basis for recommendations. But, says Glick, the company may be soon heading toward a fundamentally different approach.

“Amazon,” Glick explains, “is using the Emmy award to flaunt its latest Video Finder service, that seems to leave CF behind and embrace a new semantic approach to recommendation.”

Amazon is embracing semantics for its video content because it realizes that video is different than regular consumer items. TV and movies are “entertainment that is consumed based on personal tastes and our particular mood at the moment.  The types of content each of us enjoy is not based on what ‘other people have also watched’, rather it has to do with the plots, moods, style and pace,” he writes. “So content has to be described and discovered the same way we choose and experience it.”

Categories in Amazon’s Video Finder service  include classifications that describe the mood, plot, style and pace of titles — meaningful classifications that Glick says are the basis for semantic discovery. You can read the entire piece here.