Stock Forecasting Based on Random Forest and ARIMA Models

Abstract

In this paper, a Random Forest model and an ARIMA model are established to predict stock closing prices. The data from six Chinese stocksShandong Gold Mining, WanYi Technology, iFLYTEK, Space-Time Technology, TianYue Advanced Materials Technology, and Harmontronics Intelligent Technologyspanning from January 1, 2024, to December 30, 2024, are used. The results show that these two models are more accurate in short-term stock price prediction. By combining and comparing these two models, we conclude that the Random Forest model predicts the next day's closing price highly accurately and has obvious advantages in ultra-short-term trading. This offers insights for investors and related researchers in pursuit of short-term profits.