Unless they've made significant improvements, this thing is borderline useless.<p>About all it does is act as a nice PR/gimmick. Magic thinking.<p>When last I checked about 5 years ago, they were including client-based stats in the analysis (time per move, focus, and timing between clicks to pick a piece up and drop a piece).<p>The issue with doing that is the client is fungible, you can set any state you want locally; and so by manipulating these stats you could skew the input going into these models.<p>To give people a layman's short overview of the model:<p>It uses a several CNN Pooling Layers for feature detection and LSTM (attention embeddings) in a siamese network architecture.<p>CNN models notoriously fail to detect features that that are larger than its kernel size.<p>The LSTM embeddings can only be as useful as the features that it is trying to detect.<p>There were a number of problems with the model at the time, a high false positive rate, overfitting, and too much weight was being given to client-controllable input.<p>When the client-controllable input was held stable (constant). Certain book openings would be skewed with additional weight towards a false positive, and earlier book moves activated more often than lesser seen positions.<p>I brought the issues up to ornicar years ago in an issue, but they closed the issue without comment. The posts are mostly gone now.<p>There were a number of disagreements (mostly about certain people with admin privileges abusing their authority, not sure if it was ornicar or one of their flunkies; either way not important just completely unprofessional).<p>I guess it was good enough for them despite the high false positive rate (driving account churn).