[Paper Review] The Random Forest Model for Analyzing and Forecasting the US Stock Market in the Context of Smart Finance

Jiajian Zheng, Xin Duan+3 more|arXiv (Cornell University)|Feb 27, 2024

Economic and Technological Systems Analysis25 citations

TL;DR

The paper evaluates random forest models combined with AI to forecast stock-trend directions (rising, sideways, falling) on a test set of four US stocks, focusing on predictive accuracy and time efficiency using optimal parameters.

ABSTRACT

The stock market is a crucial component of the financial market, playing a vital role in wealth accumulation for investors, financing costs for listed companies, and the stable development of the national macroeconomy. Significant fluctuations in the stock market can damage the interests of stock investors and cause an imbalance in the industrial structure, which can interfere with the macro level development of the national economy. The prediction of stock price trends is a popular research topic in academia. Predicting the three trends of stock pricesrising, sideways, and falling can assist investors in making informed decisions about buying, holding, or selling stocks. Establishing an effective forecasting model for predicting these trends is of substantial practical importance. This paper evaluates the predictive performance of random forest models combined with artificial intelligence on a test set of four stocks using optimal parameters. The evaluation considers both predictive accuracy and time efficiency.

Motivation & Objective

• Motivate the study by the importance of stock market prediction for investors, financing costs, and macroeconomic stability.
• Aim to forecast stock price trends (rising, sideways, falling) to aid buy/hold/sell decisions.
• Investigate the predictive performance of random forest models with AI on a small, controlled set of stocks.
• Examine both predictive accuracy and time efficiency to assess practical viability.

Proposed method

• Apply random forest models augmented with artificial intelligence techniques to forecast stock trend directions.
• Use a test set consisting of four US stocks.
• Tune and employ optimal parameters for the random forest models.
• Evaluate model performance with respect to predictive accuracy and computation time.

Experimental results

Research questions

• RQ1 Can a random forest model with AI effectively forecast stock price trend directions (rising, sideways, falling) for US stocks?
• RQ2 What is the predictive accuracy of the RF+AI approach on the selected four-stock test set?
• RQ3 How does the RF+AI model perform in terms of time efficiency compared with alternative forecasting approaches?
• RQ4 Do optimal parameter settings meaningfully improve forecasting performance and efficiency?

Key findings

• The study evaluates predictive performance of random forest models combined with AI on a test set of four stocks.
• Optimal parameters are used to tune the RF models for forecasting stock trends.
• The evaluation considers both predictive accuracy and time efficiency, highlighting the approach's feasibility for practical forecasting.
• The results illustrate the RF+AI framework can be applied to forecast stock trends in the smart finance context.