Applications of Deep Learning and Machine Learning in Trading
This paper reviews how advanced computer techniques, like machine learning and deep learning, are being used to predict stock prices and improve trading strategies. It highlights the strengths and weaknesses of these methods compared to traditional trading approaches.
Content & Liability Disclaimer
This article and its accompanying video are automated summaries derived from the original research paper by Unknown authors. The original research was conducted solely by the paper's authors; PDFdigest did not conduct any of the research and makes no claims of ownership over the underlying scientific work.
The video narration is generated by artificial intelligence and references the paper's authors for attribution. The video is not narrated by any of the paper's authors. This content may contain inaccuracies, omissions, or misinterpretations of the original research. First-person language (e.g., "we found", "our results") reflects the original authors' voice, not PDFdigest's. Always read the original paper for accurate, verified information before making any decisions based on this content.
This content is provided "as is" without any warranties, express or implied. Simulated systems OÜ, its officers, directors, employees, and agents shall not be liable for any direct, indirect, incidental, special, consequential, or punitive damages arising from your use of, reliance on, or access to this content, including but not limited to errors, omissions, or misinterpretations of the original research. This disclaimer applies to the fullest extent permitted by applicable law.
- 1 Machine learning and deep learning can outperform traditional trading strategies.
- 2 Different algorithms have varying success depending on market conditions.
- 3 LSTM networks and random forests are particularly effective in generating returns and managing risk.
- 4 Performance of models can decline during volatile market periods.
Introduction
The introduction discusses the importance of accurately forecasting stock prices and the limitations of traditional strategies. It highlights the role of machine learning and deep learning in capturing complex patterns and handling unstructured data, as well as the impact of algorithmic trading on market volatility.
Literature Review
This section reviews existing literature on the application of machine learning and deep learning in stock price forecasting, focusing on recent developments and methodologies.
Machine Learning
An overview of various machine learning algorithms applied to analyze historical data and predict market trends, setting the stage for more detailed discussions on specific algorithms.
How PDFdigest Helps You Understand Research
Instant Paper Analysis
Get structured summaries and key findings from dense PDFs in seconds.
Visual Explanations
Turn complex methods, figures, and results into clearer visual breakdowns.
AI-Powered Q&A
Ask focused questions and get answers grounded in the paper.
Support Vector Machine/SVM
This section details the SVM algorithm, its application in forecasting price direction, and its performance in different market conditions, particularly during wartime.
Random Forest
The random forest model is discussed, including its training on stock returns and its performance metrics, highlighting its stability and risk management capabilities compared to other models.
Figures Explained
The paper’s visual material highlights the workflow and the main system components.
- Figure 1: Advances in Economics and Management Research ICBES 2025 ISSN:2790-1661Volume-14-(2025).
- Figure 2 :: Figure 2: Performance of DNN, gradient-boost trees, random forests, and ensembles at periods 12/1992-03/2001, 04/2001-08/2008, 09/2008-12/2009, and 01/2010-10/2015. From “Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500,” by Krauss,C., Do, X. A., & Huck, N. However, compared to other models, such as random forests, gradient-boosted trees, and ensembles, DNN has the worst performance [4] . Its average daily returns prior to and after transaction costs are 0.33% and 0.13%, respectively [4] . The directional accuracy was ranked the lowest, at around 54% [4] . Moreover, it has demonstrated the highest drawdown of 95% after transaction costs [4] . As shown in Figure2, researchers noticed that DNN performed the worst during the 2008 financial crisis, while other models were able to generate profits [4] . By changing the number of nodes in the first hidden layer, the study showed that it does not affect the overall performance of the strategy; however, the returns drop significantly if one of the hidden layers is removed, resulting in dropout regularization and choosing tanh as the activation function [4] .
- Figure 3 :: Figure 3: TDQN algorithm for Apple stock in the test set.
Frequently Asked Questions
This paper reviews how advanced computer techniques, like machine learning and deep learning, are being used to predict stock prices and improve trading strategies. It highlights the strengths and weaknesses of these methods compared to traditional trading approaches.
The introduction discusses the importance of accurately forecasting stock prices and the limitations of traditional strategies. It highlights the role of machine learning and deep learning in capturing complex patterns and handling.
Machine learning and deep learning can outperform traditional trading strategies. Different algorithms have varying success depending on market conditions. LSTM networks and random forests are particularly effective in generating returns and managing risk.
Yes. PDFDigest can turn this paper into a structured explanation, key takeaways, visual summaries, and a narrated video when available.