Predictive Modeling with Delayed Information: a Case Study in E-commerce Transaction Fraud Control

TL;DR

This paper addresses the challenge of predictive modeling in e-commerce fraud detection when transaction labels are delayed, proposing frameworks that utilize mature and partially mature data to improve environment estimation accuracy.

Contribution

Introduces CEI and FEI frameworks that leverage long-term and short-term data to enhance probabilistic environment estimation in delayed label scenarios.

Findings

Frameworks significantly improved environment estimation accuracy.

Multiple learning methods tested, including neural networks and tree-based models.

Results demonstrated better fraud detection performance in real-world Microsoft data.

Abstract

In Business Intelligence, accurate predictive modeling is the key for providing adaptive decisions. We studied predictive modeling problems in this research which was motivated by real-world cases that Microsoft data scientists encountered while dealing with e-commerce transaction fraud control decisions using transaction streaming data in an uncertain probabilistic decision environment. The values of most online transactions related features can return instantly, while the true fraud labels only return after a stochastic delay. Using partially mature data directly for predictive modeling in an uncertain probabilistic decision environment would lead to significant inaccuracy on risk decision-making. To improve accurate estimation of the probabilistic prediction environment, which leads to more accurate predictive modeling, two frameworks, Current Environment Inference (CEI) and Future Environment Inference (FEI), are proposed. These frameworks generated decision environment related features using long-term fully mature and short-term partially mature data, and the values of those features were estimated using varies of learning methods, including linear regression, random forest, gradient boosted tree, artificial neural network, and recurrent neural network. Performance tests were conducted using some e-commerce transaction data from Microsoft. Testing results suggested that proposed frameworks significantly improved the accuracy of decision environment estimation.