One obvious thing to anyone living in NYC is how tourists cluster in certain areas. I was curious about the larger patterns around this, so I spent some time looking at data. The thing I wanted to understand is: what areas are dominated by tourists? Or conversely, what areas are dominated by locals?

During my time at Spotify, I’ve reviewed thousands of resumes and interviewed hundreds of people. Lots of them were rejected but lots of them also got offers. Finally, I’ve also had my share of offers rejected by the candidate.

From my presentation at MLConf, one of the points I think is worth stressing again is how extremely well combining different algorithms works.

In this case, we’re training machine learning algorithms on different data sets (playlists, play counts, sessions) and different objectives (least squares, max likelihood). Then we combine all the models using gradient boosted decision trees training on a smaller but higher quality data set. Finally, we validate on a third data set, in this case looking at recall for a ground truth data set of related artists.

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. I ran this strategy for a basket of approximately 20 stock markets.

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. You also want to define a metric that has as high signal to noise ratio. And of course, most importantly, your metric should ideally correlate to high level business impact as much as possible.