Two Case Studies: Production ML infrastructure and Recommendation Engines - ML 072
Adventures in Machine Learning
00:00
How to Solve the Cold Start Problem in E-Commerce
A good starting place is often collaborative filtering, or just pretty sometimes complex rules. You can also use some sort of predictive models, but then you ended up something that I think is really interesting, which is the cold start problem. That's a topic that we could probably have six entire episodes just focusing on. There's ways to do that that vary in complexity; at the easiest thing to do is just calculate popularity.
Transcript
Play full episode
