A Time Series Approach to Explainability for Neural Nets with Applications to Risk-Management and Fraud Detection

TL;DR

This paper introduces a novel explainability technique for deep learning models applied to time series data, addressing the limitations of classical XAI methods in handling dependence and non-stationarity, with applications in finance.

Contribution

The paper proposes a new XAI approach specifically designed for time series data that maintains temporal order and accounts for dependence structures, improving interpretability in finance applications.

Findings

Effective explanation of neural network decisions on time series data

Improved interpretability over classical XAI methods for longitudinal data

Potential applications in risk management and fraud detection

Abstract

Artificial intelligence is creating one of the biggest revolution across technology driven application fields. For the finance sector, it offers many opportunities for significant market innovation and yet broad adoption of AI systems heavily relies on our trust in their outputs. Trust in technology is enabled by understanding the rationale behind the predictions made. To this end, the concept of eXplainable AI emerged introducing a suite of techniques attempting to explain to users how complex models arrived at a certain decision. For cross-sectional data classical XAI approaches can lead to valuable insights about the models' inner workings, but these techniques generally cannot cope well with longitudinal data (time series) in the presence of dependence structure and non-stationarity. We here propose a novel XAI technique for deep learning methods which preserves and exploits the natural time ordering of the data.