Factor-Based Conditional Diffusion Model for Contextual Portfolio Optimization

arXiv stat.ML / 4/17/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces a conditional diffusion model that forecasts the conditional distribution of next-day stock returns using high-dimensional, asset-specific factors for contextual portfolio optimization.
It uses a Diffusion Transformer with token-wise conditioning to connect each asset’s predicted returns to its own factor vector while modeling complex dependencies across assets.
The authors generate samples from the learned conditional return distribution to run daily mean-variance and mean-CVaR portfolio optimization while accounting for transaction costs and realistic constraints.
Experiments on China’s A-share market show consistent outperformance over several standard benchmarks across multiple risk-adjusted metrics.
The study includes theoretical error analysis, quantifying how approximation errors from the diffusion model propagate into the downstream portfolio optimization results.

Abstract

We propose a novel conditional diffusion model for contextual portfolio optimization that learns the cross-sectional distribution of next-day stock returns conditioned on high-dimensional asset-specific factors. Our model leverages a Diffusion Transformer architecture with token-wise conditioning, which enables linking each asset's return to its own factor vector while capturing complex cross-asset dependencies. By drawing generative samples from the learned conditional return distribution, we perform daily mean-variance and mean-CVaR optimization, incorporating transaction costs and realistic constraints. Using data from the Chinese A-share market, we demonstrate that our approach consistently outperforms various standard benchmarks across multiple risk-adjusted performance metrics. Furthermore, we provide a theoretical error analysis that quantifies the propagation of distributional approximation errors from the conditional diffusion model to the downstream portfolio optimization task. Our results demonstrate the potential of generative diffusion models in high-dimensional data-driven contextual stochastic optimization and financial decision making.