Radar improves portfolio risk models by learning from past market regimes
Retrieval-Augmented Diffusion Modeling for Stochastic Discount Factor Portfolios
Machine Learning
Summary
Managing investment portfolios is hard because financial markets change over time in unpredictable ways. The authors created a method called RADAR that looks at similar past market situations to better understand current risks. Unlike older methods that assume all uncertainties behave the same, RADAR adapts to different types of financial uncertainty with smarter noise models. Tests showed RADAR gives better results on important financial measures while producing meaningful signals about returns and how assets move together.
What this means in practice
- •For quantitative finance teams: Enhance portfolio risk models by integrating context-aware noise distributions based on historical market states for improved investment decisions.
- •For financial data engineers: Build market representation systems that condition on similar past regimes to better denoise multimodal financial data inputs like prices and news.
Authors
Kelvin J. L. Koa, Xinyang Li, Ke-Wei Huang
Abstract
In this work, we study portfolio optimization under the stochastic discount factor (SDF) framework by learning market state representations that capture the underlying risk structures of financial data. This is challenging due to several factors: financial markets exhibit non-stationary dynamics with shifting regimes, multimodal inputs such as price and news data often contain stochastic noise, and existing diffusion-based approaches, while effective for modeling stochastic dynamics, rely on assumptions such as isotropic Gaussian noise that fail to capture the state-dependent nature of financial uncertainty. To address these challenges, we introduce RADAR, a retrieval-augmented diffusion framework that learns market representations by conditioning on similar historical regimes. RADAR leverages retrieval to construct context-dependent noise distributions, applies conditional diffusion to denoise multimodal representations, and initializes the diffusion process using empirical statistics to reflect state-dependent uncertainty. Experiments show that RADAR achieves state-of-the-art performance on key risk-adjusted metrics while producing economically meaningful signals on asset returns and correlations.