Recurrent Neural Networks

Multi-Horizon Echo State Network Prediction of Intraday Stock Returns ArXiv ID: 2504.19623 “View on arXiv” Authors: Giovanni Ballarin, Jacopo Capra, Petros Dellaportas Abstract Stock return prediction is a problem that has received much attention in the finance literature. In recent years, sophisticated machine learning methods have been shown to perform significantly better than ‘‘classical’’ prediction techniques. One downside of these approaches is that they are often very expensive to implement, for both training and inference, because of their high complexity. We propose a return prediction framework for intraday returns at multiple horizons based on Echo State Network (ESN) models, wherein a large portion of parameters are drawn at random and never trained. We show that this approach enjoys the benefits of recurrent neural network expressivity, inherently efficient implementation, and strong forecasting performance. ...

Unified GARCH-Recurrent Neural Network in Financial Volatility Forecasting ArXiv ID: 2504.09380 “View on arXiv” Authors: Unknown Abstract In this study, we develop a unified volatility modeling framework that embeds GARCH dynamics directly within recurrent neural networks. We propose two interpretable hybrid architectures, GARCH-GRU and GARCH-LSTM, that integrate the GARCH(1,1) volatility update into the multiplicative gating structure of GRU and LSTM cells. This unified design preserves economically meaningful GARCH parameters while enabling the networks to learn nonlinear temporal dependencies in financial time series. Comprehensive out-of-sample evaluations across major U.S. equity indices show that both models consistently outperform classical GARCH specifications, pipeline-style hybrids, and neural baselines such as the Transformer across multiple metrics (MSE, MAE, SMAPE, and out-of-sample R\textsuperscript{“2”}). Within this family, the GARCH-GRU achieves the strongest accuracy-efficiency tradeoff, training nearly three times faster than GARCH-LSTM while maintaining comparable or superior forecasting accuracy under normal market conditions and delivering stable and economically plausible parameter estimates. The advantages persist during extreme market turbulence. In the COVID-19 stress period, both architectures retain superior forecasting accuracy and deliver well-calibrated 99 percent Value-at-Risk forecasts, achieving lower violation ratios and competitive Pinball losses relative to all benchmarks. Overall, the findings underscore the effectiveness of embedding GARCH dynamics within recurrent neural architectures, yielding models that are accurate, efficient, interpretable, and robust for real-world risk-aware volatility forecasting. ...

Leveraging RNNs and LSTMs for Synchronization Analysis in the Indian Stock Market: A Threshold-Based Classification Approach ArXiv ID: 2409.06728 “View on arXiv” Authors: Unknown Abstract Our research presents a new approach for forecasting the synchronization of stock prices using machine learning and non-linear time-series analysis. To capture the complex non-linear relationships between stock prices, we utilize recurrence plots (RP) and cross-recurrence quantification analysis (CRQA). By transforming Cross Recurrence Plot (CRP) data into a time-series format, we enable the use of Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) networks for predicting stock price synchronization through both regression and classification. We apply this methodology to a dataset of 20 highly capitalized stocks from the Indian market over a 21-year period. The findings reveal that our approach can predict stock price synchronization, with an accuracy of 0.98 and F1 score of 0.83 offering valuable insights for developing effective trading strategies and risk management tools. ...

Recurrent Neural Networks with more flexible memory: better predictions than rough volatility ArXiv ID: 2308.08550 “View on arXiv” Authors: Unknown Abstract We extend recurrent neural networks to include several flexible timescales for each dimension of their output, which mechanically improves their abilities to account for processes with long memory or with highly disparate time scales. We compare the ability of vanilla and extended long short term memory networks (LSTMs) to predict asset price volatility, known to have a long memory. Generally, the number of epochs needed to train extended LSTMs is divided by two, while the variation of validation and test losses among models with the same hyperparameters is much smaller. We also show that the model with the smallest validation loss systemically outperforms rough volatility predictions by about 20% when trained and tested on a dataset with multiple time series. ...

Stochastic Delay Differential Games: Financial Modeling and Machine Learning Algorithms ArXiv ID: 2307.06450 “View on arXiv” Authors: Unknown Abstract In this paper, we propose a numerical methodology for finding the closed-loop Nash equilibrium of stochastic delay differential games through deep learning. These games are prevalent in finance and economics where multi-agent interaction and delayed effects are often desired features in a model, but are introduced at the expense of increased dimensionality of the problem. This increased dimensionality is especially significant as that arising from the number of players is coupled with the potential infinite dimensionality caused by the delay. Our approach involves parameterizing the controls of each player using distinct recurrent neural networks. These recurrent neural network-based controls are then trained using a modified version of Brown’s fictitious play, incorporating deep learning techniques. To evaluate the effectiveness of our methodology, we test it on finance-related problems with known solutions. Furthermore, we also develop new problems and derive their analytical Nash equilibrium solutions, which serve as additional benchmarks for assessing the performance of our proposed deep learning approach. ...