Momentum strategies 2014-03-03 Haven't posted anything in ages, so here's a quick hack I threw together in Python on a Sunday night. Basically I wanted to know whether momentum strategies work well for international stock indexes. I spent a bit of time putting together a strategy that buys the stock index if the return during the previous n days was positive, otherwise doesn't do anything. Read more…
Ratio metrics 2014-01-23 We run a ton of A/B tests at Spotify and we look at a ton of metrics. Defining metrics is a little bit of an art form. Ideally you want to define success metrics before you run a test to avoid cherry picking metrics. Read more…
Benchmarking nearest neighbor libraries in Python 2014-01-12 Radim Rehurek has put together an excellent summary of approximate nearest neighbor libraries in Python. This is exciting, because one of the libraries he's covering, annoy, was built by me. After introducing the problem, he goes through the list of contestants and sticks with five remaining ones. Read more…
More recommender algorithms 2013-12-20 I wanted to share some more insight into the algorithms we use at Spotify. One matrix factorization algorithm we have used for a while assumes that we have user vectors $$ bf{a}_u $$ and item vectors $$ bf{b}_i $$ . Read more…
Microsoft's new marketing strategy: give up 2013-12-12 I think it's funny how MS at some point realized they are not the cool kids and there's no reason to appeal to that target audience. Their new marketing strategy finally admits what's been long known: the correlation between “business casual” and using Microsoft products: Read more…
Bagging as a regularizer 2013-12-06 One thing I encountered today was a trick using bagging as a way to go beyond a point estimate and get an approximation for the full distribution. This can then be used to penalize predictions with larger uncertainty, which helps reducing false positives. Read more…
Model benchmarks 2013-11-02 A lot of people have asked me what models we use for recommendations at Spotify so I wanted to share some insights. Here's benchmarks for some models. Note that we don't use all of them in production. Read more…