Predicting Branch Visits and Upselling using Temporal Banking Data

There is an abundance of temporal and non-temporal data in banking (and other industries), but such temporal activity data can not be used directly with classical machine learning models. In this work, we perform extensive feature extraction from the temporal user activity data in an attempt to predict user visits to different branches and credit card upselling as part of ECML/PKDD Discovery Challenge 2016. Our solution ranked 4 for Task 1 and achieved an AUC of 0.7056 for Task 2 on public leaderboard.