Ask HN: Recommender systems (Amazon, Spotify, Netflix etc.) getting any better?
Recommendation systems are arguably low-hanging fruits for popular machine learning algorithms. How good are recommendation systems (book recommendation, shopping bundles, songs you might like etc.) in your experience over the years?
2 comments
Check what those companies spend on data science teams, and rethink “low hanging fruit.” It’s incredibly nuanced once you solve the easy wins.
Low-hanging in the following sense: the premise - I tell you what I like, you tell me what else I might like - is compelling for the consumer, therefore, input is not the limiting factor. Moreover, recommender systems at such massive companies must be particularly amenable to A/B testing to help profile their customers more accurately. Finally, performance metrics are straightforward and easy to calculate.