Adaptive Fraud Detection System Using Dynamic Risk Features
This addresses the issue of rapidly changing fraud patterns for eCommerce merchants, but it is incremental as it builds on existing statistical learning frameworks.
The paper tackles the problem of concept drift in eCommerce fraud detection by proposing dynamic risk features, and validates that the dynamic model achieves a superior ROC curve compared to a static model in production.
eCommerce transaction frauds keep changing rapidly. This is the major issue that prevents eCommerce merchants having a robust machine learning model for fraudulent transactions detection. The root cause of this problem is that rapid changing fraud patterns alters underlying data generating system and causes the performance deterioration for machine learning models. This phenomenon in statistical modeling is called "Concept Drift". To overcome this issue, we propose an approach which adds dynamic risk features as model inputs. Dynamic risk features are a set of features built on entity profile with fraud feedback. They are introduced to quantify the fluctuation of probability distribution of risk features from certain entity profile caused by concept drift. In this paper, we also illustrate why this strategy can successfully handle the effect of concept drift under statistical learning framework. We also validate our approach on multiple businesses in production and have verified that the proposed dynamic model has a superior ROC curve than a static model built on the same data and training parameters.