"Search and recommendation is the overarching topic of this talk. As we all know, search and recommendations as application of machine learning is omnipresent in different products. Whether it's video streaming services like Netflix or Hulu or Amazon, or music streaming services such as Spotify, Pandora, eCommerce platforms such as Etsy, Amazon, leverages ML, machine learning and AI for search and recommendations use cases."
"The user base as well as the catalog is ever growing. How many folks are aware of search and recommendation and applications of ML? Usually, because the catalog is really big, in reality, for B2C, business to customer products, let's say if it's a big company like Netflix or Spotify, there are 100 million plus users. Netflix has 300 million plus users. The catalog, the items over which we have to score to show to a user is usually more than 100 million."
Search and recommendation apply machine learning across video streaming (Netflix, Hulu, Amazon), music streaming (Spotify, Pandora), and e-commerce (Etsy, Amazon). User bases and catalogs continually grow, often reaching hundreds of millions of users and items; some companies have catalogs in the billions. Scoring an entire catalog per user is infeasible, so systems use a two-stage approach: an initial candidate-selection or retrieval stage reduces millions of items to hundreds of thousands, followed by a ranking stage to order those candidates for personalized presentation. Latency constraints necessitate fast retrieval to avoid unacceptable user delays on device startup.
Read at InfoQ
Unable to calculate read time
Collection
[
|
...
]