Introduction to Recommender Systems in 2018

My Take

Recommender systems are a great example of how machine learning can captures incremental benefits in the eCommerce industry. Every eCommerce company necessarily has to have the capability to surface their products for people who want them, but the sophistication of that capability varies wildly. You can run a competent eCommerce site simply by showing an unsorted list of all your products – but you can almost certainly do better. That’s where incremental optimizations such as recommender systems come into play. This piece also does a good job of discussing the importance of testing and validating the incremental benefit of such systems – very easy to forget in a fast-paced business.

Their Take

Many e-commerce and retail companies are leveraging the power of data and boosting sales by implementing recommender systems on their websites. In short, these systems aim to predict users’ interests and recommend items that quite likely are interesting for them. Data required for recommender systems stems from explicit user ratings after watching a movie or listening to a song, from implicit search engine queries and purchase histories, or from other knowledge about the users/items themselves. Sites like Spotify, YouTube or Netflix use that data in order to suggest playlists, so-called Daily mixes, or to make video recommendations, respectively.

https://tryolabs.com/blog/introduction-to-recommender-systems/