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

作者：J. Bian, Jiaxin Lin · 发表于：Advances in economics, business and management research/Advances in Economics, Business and Management Research · 年份：2025 · DOI：10.2991/978-94-6463-652-9_70 · 被引用次数：3 · 研究领域：Stock Market Forecasting Methods

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 investmen...