Adapting to Concept Drift in Credit Card Transaction Data Streams Using Contextual Bandits and Decision Trees

Authors

  • Dennis Soemers Vrije Universiteit Brussel
  • Tim Brys Vrije Universiteit Brussel
  • Kurt Driessens Maastricht University
  • Mark Winands Maastricht University
  • Ann Nowé Vrije Universiteit Brussel

Keywords:

fraud, credit card, contextual bandit, decision tree, concept drift

Abstract

Credit card transactions predicted to be fraudulent by automated detection systems are typically handed over to human experts for verification. To limit costs, it is standard practice to select only the most suspicious transactions for investigation. We claim that a trade-off between exploration and exploitation is imperative to enable adaptation to changes in behavior (concept drift). Exploration consists of the selection and investigation of transactions with the purpose of improving predictive models, and exploitation consists of investigating transactions detected to be suspicious. Modeling the detection of fraudulent transactions as rewarding, we use an incremental Regression Tree learner to create clusters of transactions with similar expected rewards. This enables the use of a Contextual Multi-Armed Bandit (CMAB) algorithm to provide the exploration/exploitation trade-off. We introduce a novel variant of a CMAB algorithm that makes use of the structure of this tree, and use Semi-Supervised Learning to grow the tree using unlabeled data. The approach is evaluated on a real dataset and data generated by a simulator that adds concept drift by adapting the behavior of fraudsters to avoid detection. It outperforms frequently used offline models in terms of cumulative rewards, in particular in the presence of concept drift.

Downloads

Published

2018-04-27

How to Cite

Soemers, D., Brys, T., Driessens, K., Winands, M., & Nowé, A. (2018). Adapting to Concept Drift in Credit Card Transaction Data Streams Using Contextual Bandits and Decision Trees. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11411