Fraud Regulating Policy for E-Commerce via Constrained Contextual Bandits

Fraud sellers in e-commerce often promote themselves via fake visits or purchases to increase sales, jeopardizing the business environment of the platform. How to regulate the exposure of these sellers to buyers without affecting normal online business remains a challenging problem, since blocking them entirely without discrimination may kill the normal transactions and could potentially decrease the total transactions of the platform. To address this problem, we introduce a regulating valve which blocks fraud sellers with a certain probability. To learn the optimal blocking policy, we model the regulating valve as a contextual bandit problem with a constraint on the total transaction decline. Since existing bandit algorithms are unable to incorporate the transaction constraint, we propose a novel bandit algorithm, which decides the policy based on a set of neural networks and iteratively updates the neural networks with online observations and the constraint. Experiments on synthetic data and one of the largest e-commerce platforms in the world both show that our algorithm effectively and efficiently outperforms existing bandit algorithms by a large margin.