Differential LSTM (D-LSTM): Integrating Differential Operators Into LSTM Cells for Financial Time-Series Forecasting
Open Access
- 6 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 21674-21705
Abstract
While Long Short-Term Memory (LSTM) networks are pivotal for time-series forecasting, their fixed recurrent structure struggles to capture the complex dynamics of financial markets, such as abrupt volatility shifts and persistent trends. This study proposes a physics-inspired recurrent architecture, named Differential Long Short-Term Memory (D-LSTM), that embeds diffusion and dissipation operators directly into the cell-state evolution. These operators jointly capture how information propagates across time, how volatility dissipates, and how memory decays in dynamic financial environments. The model integrates the interpretability of differential equations with the predictive power of deep learning, forming a mathematically grounded recurrent structure. To ensure rigorous validation, D-LSTM is benchmarked against standard LSTM and self-attention LSTM (SA-LSTM) models across three heterogeneous financial datasets: Crude Oil (WTI), Gold, and NASDAQ Composite Index, covering the period 2014–2024. The results demonstrate that D-LSTM achieves a statistically significant improvement in predictive accuracy across all assets, as measured by MAE, RMSE, and R2 scores. Critically, our extensive ablation studies reveal that the model’s components have a data-dependent efficacy. The full architecture excels on the volatile oil series, whereas more parsimonious configurations are superior for the strongly trending gold and NASDAQ data. This research establishes D-LSTM not as a monolithic model, but as a flexible and robust framework for financial forecasting. Our findings underscore the critical importance of aligning architectural complexity with the statistical properties of the time series, offering a new paradigm for designing more adaptive and effective predictive models.Keywords
This publication has 34 references indexed in Scilit:
- A critical review of RNN and LSTM variants in hydrological time series predictionsMethodsX, 2024
- Avoiding common machine learning pitfallsPatterns, 2024
- Overfitting, Underfitting and General Model Overconfidence and Under-Performance Pitfalls and Best Practices in Machine Learning and AI2024
- Challenges of Stock Prediction Based on LSTM Neural Network2024
- CO2 concentration forecasting in smart cities using a hybrid ARIMA–TFT model on multivariate time series IoT dataScientific Reports, 2023
- Neural modal ordinary differential equations: Integrating physics-based modeling with neural ordinary differential equations for modeling high-dimensional monitored structuresData-Centric Engineering, 2022
- Temporal Fusion Transformers for interpretable multi-horizon time series forecastingInternational Journal of Forecasting, 2021
- A CNN-BiLSTM-AM method for stock price predictionNeural Computing and Applications, 2020
- Financial time series forecasting with deep learning : A systematic literature review: 2005–2019Applied Soft Computing, 2020
- Forecasting the volatility of stock price index: A hybrid model integrating LSTM with multiple GARCH-type modelsExpert Systems with Applications, 2018