Skip to content
Book Open access

Disentangled Dual-Granularity Learning for Market-Adaptive Stock Return Forecasting under Non-Stationary Environments

Aug 2026 · Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 · 0 citations · 52 references

TL;DR

The proposed Disentangled Dual-Granularity Learning Network (DDGL-Net) outperforms state-of-the-art baselines on real-world stock datasets, validating the effectiveness of disentangled modeling and regime-aware adaptation.

Abstract

Deep learning has emerged as a prominent paradigm in stock return forecasting, demonstrating remarkable capabilities in extracting non-linear patterns from historical stock data. However, existing approaches often process stock features as a monolithic input with fixed temporal receptive fields. This structural inflexibility fails to distinguish transient microstructure fluctuations and persistent long-term trends, resulting in entangled representations that impede adaptation to non-stationary environments. To address these issues, we propose the Disentangled Dual-Granularity Learning Network (DDGL-Net) to decouple and integrate diverse temporal signals. Specifically, we first construct a Disentangled Dual-Granularity Encoder (DDGE) to isolate fine-grained short-term and coarse-grained long-term features via parallel streams. To fuse dual-granularity temporal representations, we introduce a Market-Adaptive Contextual Modulator (MACM) as a regime-aware filter, which leverages global market context to dynamically reweight granularity contributions. Recognizing that input modulation alone is insufficient for the non-stationary latent-to-return mapping, we devise a Hybrid Residual Mixture of Experts (HR-MoE) predictor to decompose forecasts into stable consensus and adaptive residuals, ensuring resilient performance across shifting regimes. Extensive experiments confirm that DDGL-Net outperforms state-of-the-art baselines on real-world stock datasets, validating the effectiveness of disentangled modeling and regime-aware adaptation.

Read PDF

Similar papers

Open access Sep 2026

Enhancing TimeXer with TCN and differential attention for multivariate stock forecasting

DAT-TimeXer is proposed, a structure-aware adaptation of TimeXer for closing-price forecasting that achieves the lowest mean forecasting errors among the compared models in the one-step evaluations and maintains lower errors at horizons of 1, 3, 5, and 10 in the evaluated multi-step tasks.

Si-Xing Liu, Quan-Xiang Lan, Jing Zhang et al. · 0 citations
Open access 2026

DAE-SRP: A Deep Auto-Encoder Framework for Denoised Stock Return Prediction

Predicting stock returns remains challenging because financial time series are inherently noisy and driven by unobserved dynamic factors. Although numerous deep learning models exist, they typically process raw price data end-to-end. This direct processing makes them prone to overfitting and unable to capture underlyin...

Kanghyeon Seo, Yoojeong Song · 0 citations
#artificial intelligence Open access Jul 2026

A Hybrid LSTM–XGBoost Framework for Multi-Horizon Stock Return Prediction Across Diversified Equity Portfolios

Accurate prediction of equity returns remains a major challenge in computational finance due to the non-stationary, nonlinear, and low signal-to-noise ratio nature of financial time series. This paper proposes a hybrid two-stage architecture that combines a long short-term memory (LSTM) network with an XGBoost gradient...

Seifeldin Mostafa, Yahia Ahmed, Farah Darwish et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Does Joint-Embedding Predictive Architecture Pretraining Help Time Series Forecasting?

A large scale evaluation of one JEPA instantiation across nine backbones and eleven benchmarks spanning temporal and spatio-temporal forecasting finds that the benefit of this instantiation varies sharply across backbones, indicating the variability is a general property of this instantiation rather than a dataset spec...

Yu-Tong Feng, Bo-Wen Liao, See-Kiong Ng et al. · 0 citations
Preprint Sep 2026

Hierarchical Multi-Task Learning with Liquidity-Aware Signals for Stock Forecasting

Stock price forecasting is a long-standing challenge in computational finance, driven by the inherent randomness of markets and complex temporal patterns. While recent deep-learning models have raised forecasting accuracy by jointly modeling inter-stock and temporal price dynamics, they conflate inter-stock relationshi...

Heng-Yi Yang, Si-Da Lin, Yi-Yan Qi et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.