Background:<p>I wanted to make a simple machine learning project, so I came up with an idea: can you predict the winning team of a Dota match based on picks alone? Input is the team composition from both sides, and output is the probability of either team winning.<p>The data:<p>Data is from OpenDota.com (an excellent resource and a really flexible API). The source data is all professional matches on patch 7.06 and above.<p>Recommended usage:<p>I recommend you go to the matches page in OpenDota.com and paste a match ID from any of the professional matches and see the prediction. For example: 3344489368, 3337182753, 3331909193<p>Technology:<p>The backend is on node and the ML library used is brain.js. It's a great library, really easy to use even for a total ML newbie.