Bank Card Usage Prediction Exploiting Geolocation Information
This work addresses bank card usage prediction for financial applications, but it is incremental as it applies existing methods to a specific dataset.
The team tackled bank card usage prediction tasks in the ECML-PKDD 2016 Discovery Challenge by using gradient boosted decision trees with hyperparameter tuning and geolocation-based features, achieving best performance on the public leaderboard for the first task and fourth place for the second task.
We describe the solution of team ISMLL for the ECML-PKDD 2016 Discovery Challenge on Bank Card Usage for both tasks. Our solution is based on three pillars. Gradient boosted decision trees as a strong regression and classification model, an intensive search for good hyperparameter configurations and strong features that exploit geolocation information. This approach achieved the best performance on the public leaderboard for the first task and a decent fourth position for the second task.