Sequential Behavioral Data Processing Using Deep Learning and the Markov Transition Field in Online Fraud Detection

TL;DR

This paper introduces a deep learning model combining RNNs and Markov Transition Fields to improve online fraud detection by analyzing sequential behavioral data from digital transactions.

Contribution

It presents a novel RNN-based architecture integrated with MTF for enhanced fraud prediction from unstructured behavioral sequences.

Findings

Significantly improved fraud prediction accuracy over traditional methods.

Effective processing of unstructured sequential behavioral data.

Outperforms multilayer perceptron and DTW-based classifiers.

Abstract

Due to the popularity of the Internet and smart mobile devices, more and more financial transactions and activities have been digitalized. Compared to traditional financial fraud detection strategies using credit-related features, customers are generating a large amount of unstructured behavioral data every second. In this paper, we propose an Recurrent Neural Netword (RNN) based deep-learning structure integrated with Markov Transition Field (MTF) for predicting online fraud behaviors using customer's interactions with websites or smart-phone apps as a series of states. In practice, we tested and proved that the proposed network structure for processing sequential behavioral data could significantly boost fraud predictive ability comparing with the multilayer perceptron network and distance based classifier with Dynamic Time Warping(DTW) as distance metric.