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

Paper: arXiv 2212.02906

Authors: Marc Wildi, Branka Hadji Misheva

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.

Complexity vs Empirical Score

• Math Complexity: 6.5/10
• Empirical Rigor: 6.0/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper introduces a novel approach to Explainable AI specifically designed for temporal structures and non-stationary time series in financial contexts like fraud detection. It effectively balances formal deep learning mathematics with empirical risk-management applications, though full reproducibility relies on specific model implementations.

Research Flowchart

  flowchart TD
    A[Research Goal: Develop Time Series XAI<br/>for Deep Learning in Finance] --> B[Input Data: Longitudinal Finance Data<br/>Time Series with Non-Stationarity]
    B --> C[Methodology: Time-Aware XAI Approach<br/>Preserving Temporal & Dependence Structure]
    C --> D[Model Training & Explanation:<br/>Deep Learning Models for Risk & Fraud]
    D --> E[Key Outcome: Trustworthy Explanations<br/>Adapted for Complex Time Series Decisions]