top of page
  • Hélène Dufour

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

"We here propose a novel XAI [eXplainable AI] technique for deep learning methods (DL) which preserves and exploits the natural time ordering of the data. Simple applications to financial data illustrate the potential of the new approach in the context of risk-management and fraud-detection."


0 vue0 commentaire

Posts récents

Voir tout

"We respond to Tetlock et al. (2022) showing 1) how expert judgment fails to reflect tail risk, 2) the lack of compatibility between forecasting tournaments and tail risk assessment methods (such as e

bottom of page