Hierarchical Fallback Architecture for High Risk Online Machine Learning Inference

TL;DR

This paper introduces a hierarchical fallback architecture designed to enhance robustness in high-risk online machine learning applications, particularly in financial services like fraud detection using Open Banking data under extreme stress conditions.

Contribution

It presents a novel hierarchical fallback framework tailored for robustness in high-risk online ML, with detailed failure scenario analysis and real-world industry application.

Findings

Effective handling of external data failures in online inference

Improved robustness in fraud risk evaluation under stress

Practical applicability demonstrated in financial industry

Abstract

Open Banking powered machine learning applications require novel robustness approaches to deal with challenging stress and failure scenarios. In this paper we propose an hierarchical fallback architecture for improving robustness in high risk machine learning applications with a focus in the financial domain. We define generic failure scenarios often found in online inference that depend on external data providers and we describe in detail how to apply the hierarchical fallback architecture to address them. Finally, we offer a real world example of its applicability in the industry for near-real time transactional fraud risk evaluation using Open Banking data and under extreme stress scenarios.