Distributed Monitoring for Data Distribution Shifts in Edge-ML Fraud Detection

TL;DR

This paper introduces an open-source framework for continuous monitoring of data distribution shifts in distributed edge machine learning systems used for fraud detection, enhancing real-time detection accuracy.

Contribution

It presents a novel distributed KS test-based framework for monitoring data shifts in edge ML applications, addressing a key gap in fraud detection systems.

Findings

Effective detection of data distribution shifts demonstrated on real-world datasets.

Framework enables real-time monitoring with high accuracy.

Open-source implementation facilitates adoption and further research.

Abstract

The digital era has seen a marked increase in financial fraud. edge ML emerged as a promising solution for smartphone payment services fraud detection, enabling the deployment of ML models directly on edge devices. This approach enables a more personalized real-time fraud detection. However, a significant gap in current research is the lack of a robust system for monitoring data distribution shifts in these distributed edge ML applications. Our work bridges this gap by introducing a novel open-source framework designed for continuous monitoring of data distribution shifts on a network of edge devices. Our system includes an innovative calculation of the Kolmogorov-Smirnov (KS) test over a distributed network of edge devices, enabling efficient and accurate monitoring of users behavior shifts. We comprehensively evaluate the proposed framework employing both real-world and synthetic financial transaction datasets and demonstrate the framework's effectiveness.