Detection of Problem Gambling with Less Features Using Machine Learning Methods
This work addresses cost reduction for gambling operators or researchers by enabling precise detection with fewer features, but it is incremental as it builds on existing machine learning methods.
The study tackled the problem of reducing data collection costs for detecting problem gambling by proposing a deep neural network, PGN4, which maintains performance with only 5 features instead of 102, experiencing only a minor performance drop.
Analytic features in gambling study are performed based on the amount of data monitoring on user daily actions. While performing the detection of problem gambling, existing datasets provide relatively rich analytic features for building machine learning based model. However, considering the complexity and cost of collecting the analytic features in real applications, conducting precise detection with less features will tremendously reduce the cost of data collection. In this study, we propose a deep neural networks PGN4 that performs well when using limited analytic features. Through the experiment on two datasets, we discover that PGN4 only experiences a mere performance drop when cutting 102 features to 5 features. Besides, we find the commonality within the top 5 features from two datasets.