# Forecasting directional movements of stock prices for intraday trading using LSTM and random forests

arXiv: https://arxiv.org/abs/2004.10178 · HTML: https://mlsanity.com/paper/2004.10178/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2020.

## Built on by (most cited first, 13 of 13)

- [Optimal Weighted Random Forests](https://mlsanity.com/paper/2305.10042/) (2023)
- [Detecting data-driven robust statistical arbitrage strategies with deep neural networks](https://mlsanity.com/paper/2203.03179/) (2022)
- [Regression and Forecasting of U.S. Stock Returns Based on LSTM](https://mlsanity.com/paper/2502.05210/) (2025)
- [Recurrent neural network based parameter estimation of Hawkes model on high-frequency financial data](https://mlsanity.com/paper/2304.11883/) (2023)
- [Learning Representations without Compositional Assumptions](https://mlsanity.com/paper/2305.19726/) (2023)
- [Hedging Properties of Algorithmic Investment Strategies using Long Short-Term Memory and Time Series models for Equity Indices](https://mlsanity.com/paper/2309.15640/) (2023)
- [Quantum-Enhanced Forecasting for Deep Reinforcement Learning in Algorithmic Trading](https://mlsanity.com/paper/2509.09176/) (2025)
- [Big portfolio selection by graph-based conditional moments method](https://mlsanity.com/paper/2301.11697/) (2023)
- [Identifying Trades Using Technical Analysis and ML/DL Models](https://mlsanity.com/paper/2304.09936/) (2023)
- [Using a Deep Learning Model to Simulate Human Stock Trader's Methods of Chart Analysis](https://mlsanity.com/paper/2304.14870/) (2023)
- [Enhancing Multistep Prediction of Multivariate Market Indices Using Weighted Optical Reservoir Computing](https://mlsanity.com/paper/2408.00652/) (2024)
- [Risk-averse policies for natural gas futures trading using distributional reinforcement learning](https://mlsanity.com/paper/2501.04421/) (2025)
- [A Neuro-Fuzzy System for Interpretable Long-Term Stock Market Forecasting](https://mlsanity.com/paper/2510.00960/) (2025)

## Abstract (arXiv)

We employ both random forests and LSTM networks (more precisely CuDNNLSTM) as training methodologies to analyze their effectiveness in forecasting out-of-sample directional movements of constituent stocks of the S&P 500 from January 1993 till December 2018 for intraday trading. We introduce a multi-feature setting consisting not only of the returns with respect to the closing prices, but also with respect to the opening prices and intraday returns. As trading strategy, we use Krauss et al. (2017) and Fischer & Krauss (2018) as benchmark. On each trading day, we buy the 10 stocks with the highest probability and sell short the 10 stocks with the lowest probability to outperform the market in terms of intraday returns -- all with equal monetary weight. Our empirical results show that the multi-feature setting provides a daily return, prior to transaction costs, of 0.64% using LSTM networks, and 0.54% using random forests. Hence we outperform the single-feature setting in Fischer & Krauss (2018) and Krauss et al. (2017) consisting only of the daily returns with respect to the closing prices, having corresponding daily returns of 0.41% and of 0.39% with respect to LSTM and random forests, respectively.