Optimizing Investment Strategies: A Random Forest Approach to Stock Return Prediction and Portfolio Management

DOI

10.2991/978-94-6463-652-9_70How to use a DOI?

Keywords

Random Forest; Return Prediction; Machine Learning

Abstract

Quantitative finance is becoming an increasingly useful tool in modern financial markets by utilizing computational power to optimize investment strategies. The idea of Quantitative finance originated from early theories like the Efficient Market Hypothesis and Random Walk Theory proposed by Louis Bachelier in 1900. Today, machine learning has revolutionized how financial data is analyzed, with models such as Random Forest providing valuable insights for stock price prediction and portfolio management. This study focuses on employing the Random Forest model for predicting quarterly stock returns and volatilities by using financial data from the NASDAQ 100 Index. Some of the key corporate characteristics that are used in this study are net profit, return on equity (ROE), and total liabilities. The model aims to identify key factors that influence stock performance through analyzing the key characteristics. The predictions generated by the model are then used to construct optimized investment portfolios, which are tested against benchmark portfolios, the NASDAQ 100 index, in a back testing framework. The results demonstrate that the Random Forest model effectively captures patterns in stock performance and enhances decision-making in portfolio management. The results of this study also highlight the potential of machine learning in improving stock selection and asset allocation strategies. In addition, this approach is contributing to more informed decision-making in long-term investment portfolios.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jingxuan Bian
AU  - Jiaxin Lin
PY  - 2025
DA  - 2025/02/24
TI  - Optimizing Investment Strategies: A Random Forest Approach to Stock Return Prediction and Portfolio Management
BT  - Proceedings of the International Workshop on Navigating the Digital Business Frontier for Sustainable Financial Innovation (ICDEBA 2024)
PB  - Atlantis Press
SP  - 674
EP  - 681
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6463-652-9_70
DO  - 10.2991/978-94-6463-652-9_70
ID  - Bian2025
ER  -