How to Make Machine Learning Work for You

Oscar: We had the largest music curation data base in history, growing larger every minute to over four billion playlest to day. The problem with collaborative filtering is that it doesn't actually listen to the music or standing in any way. It just looks how often it appears together with other songs. So if enough people put heavy metal right next to a classical ballet on the same play less, calabate filtering will deduce that when you hit play on some metal, you might also enjoy a little swan lake. And these mistakes get at the heart of our second product, strety lesson throwing machine learning at data you don't fully understand isn't enough to give you a great