Risk Management - AI for Digital Finance 2026

LLMs in Finance Explainable AI Blockchain Security Risk Management Digital Banking Alternative Data

Overview

Modern risk management leverages artificial intelligence to process vast amounts of data, identify emerging threats, and quantify exposures across market, credit, operational, and cyber risk domains. AI enables real-time risk monitoring and more accurate stress testing scenarios. This track explores how machine learning transforms traditional risk frameworks, from VaR calculations using neural networks to climate risk modeling with advanced scenario analysis. We examine both the enhanced capabilities AI provides and the model risks it introduces to financial institutions.

Key Research Questions

How can deep learning improve Value-at-Risk (VaR) estimation accuracy?
What role does AI play in climate risk modeling and stress testing?
How should model risk management evolve to address AI/ML model risks?
Can reinforcement learning optimize dynamic hedging strategies?
How do we validate AI risk models for regulatory approval?

Methodologies

Deep learning for VaR and Expected Shortfall
Recurrent neural networks for credit risk prediction
Monte Carlo simulation with ML-generated scenarios
Ensemble methods for operational risk
Natural language processing for emerging risk identification

Industry Applications

Real-time market risk monitoring dashboards
Credit default prediction models
Operational risk event classification
Climate risk scenario generation
Cyber risk quantification

Submit Your Research