Adaptive Regime-Aware Stock Price Prediction Using Autoencoder-Gated Dual Node Transformers with Reinforcement Learning Control

2026-03-19

AI Summary

This work proposes a self-supervised adaptive framework for stock market prediction that addresses the challenge of modeling divergent market dynamics under stable versus high-volatility regimes. Unlike conventional approaches that rely on costly and outdated manual annotations of market states, the method leverages an autoencoder to dynamically detect anomalous periods—defined as those where standard models fail—via reconstruction error. A dual-path Transformer architecture separately captures patterns in stable and event-driven markets, while a Soft Actor-Critic reinforcement learning controller adaptively tunes both the anomaly detection threshold and the fusion weights between the two pathways. Evaluated on 20 S&P 500 stocks from 1982 to 2025, the model achieves an overall MAPE of 0.59% and 72% directional accuracy, with MAPE below 0.85% during high-volatility periods—substantially outperforming baselines (MAPE > 1.5%). Ablation studies confirm the contribution of each component.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Multiagent Systems: Adversarial Agents
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Stock markets exhibit regime-dependent behavior where prediction models optimized for stable conditions often fail during volatile periods. Existing approaches typically treat all market states uniformly or require manual regime labeling, which is expensive and quickly becomes stale as market dynamics evolve. This paper introduces an adaptive prediction framework that adaptively identifies deviations from normal market conditions and routes data through specialized prediction pathways. The architecture consists of three components: (1) an autoencoder trained on normal market conditions that identifies anomalous regimes through reconstruction error, (2) dual node transformer networks specialized for stable and event-driven market conditions respectively, and (3) a Soft Actor-Critic reinforcement learning controller that adaptively tunes the regime detection threshold and pathway blending weights based on prediction performance feedback. The reinforcement learning component enables the system to learn adaptive regime boundaries, defining anomalies as market states where standard prediction approaches fail. Experiments on 20 S&P 500 stocks spanning 1982 to 2025 demonstrate that the proposed framework achieves 0.68% MAPE for one-day predictions without the reinforcement controller and 0.59% MAPE with the full adaptive system, compared to 0.80% for the baseline integrated node transformer. Directional accuracy reaches 72% with the complete framework. The system maintains robust performance during high-volatility periods, with MAPE below 0.85% when baseline models exceed 1.5%. Ablation studies confirm that each component contributes meaningfully: autoencoder routing accounts for 36% relative MAPE degradation upon removal, followed by the SAC controller at 15% and the dual-path architecture at 7%.

Problem

• regime-aware prediction
• market volatility
• adaptive stock forecasting
• anomaly detection
• regime switching

Innovation

• Autoencoder-Gated Routing
• Dual Node Transformers
• Reinforcement Learning Control
• Regime-Aware Prediction
• Adaptive Market Modeling