Mitigating Distribution Shift in Stock Price Data via Return-Volatility Normalization for Accurate Prediction

2025-08-13

AI Summary

To address degraded model generalizability in stock price forecasting caused by distribution shift between training and test data, this paper proposes ReVol. Methodologically, ReVol introduces— for the first time in financial time-series modeling—joint return-volatility normalization to mitigate distribution drift; designs a learnable feature disentanglement and refusion mechanism integrated with attention modules for dynamic feature calibration; and synergistically incorporates geometric Brownian motion priors into deep neural networks to jointly capture long-term trends and short-term volatility patterns. Extensive experiments on multiple real-world stock market datasets demonstrate that ReVol significantly enhances prediction robustness and accuracy: it achieves an average information coefficient (IC) improvement of over 0.03 and a Sharpe ratio (SR) gain exceeding 0.7, consistently outperforming state-of-the-art baseline models.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Reasoning under Uncertainty: Relational Probabilistic Models
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

How can we address distribution shifts in stock price data to improve stock price prediction accuracy? Stock price prediction has attracted attention from both academia and industry, driven by its potential to uncover complex market patterns and enhance decisionmaking. However, existing methods often fail to handle distribution shifts effectively, focusing on scaling or representation adaptation without fully addressing distributional discrepancies and shape misalignments between training and test data. We propose ReVol (Return-Volatility Normalization for Mitigating Distribution Shift in Stock Price Data), a robust method for stock price prediction that explicitly addresses the distribution shift problem. ReVol leverages three key strategies to mitigate these shifts: (1) normalizing price features to remove sample-specific characteristics, including return, volatility, and price scale, (2) employing an attention-based module to estimate these characteristics accurately, thereby reducing the influence of market anomalies, and (3) reintegrating the sample characteristics into the predictive process, restoring the traits lost during normalization. Additionally, ReVol combines geometric Brownian motion for long-term trend modeling with neural networks for short-term pattern recognition, unifying their complementary strengths. Extensive experiments on real-world datasets demonstrate that ReVol enhances the performance of the state-of-the-art backbone models in most cases, achieving an average improvement of more than 0.03 in IC and over 0.7 in SR across various settings.

Problem

• Addressing distribution shifts in stock price data
• Improving stock price prediction accuracy
• Handling distributional discrepancies between training and test data

Innovation

• Return-Volatility normalization removes sample-specific characteristics
• Attention module estimates market features and reduces anomalies
• Combines geometric Brownian motion with neural networks