Prediction of Stock Industry Sectors Listed on the Indonesia Stock Exchange (IDX) based on Financial Statements with the Random Forest Method

Authors

  • I Kamil Elian Zhafran Universitas Telkom Bandung, Indonesia
  • Deni Saepudin Universitas Telkom Bandung, Indonesia

DOI:

https://doi.org/10.59141/jist.v5i10.1239

Keywords:

random forest, indonesian stock exchange, industrial sector predictions, financial reports

Abstract

This research aims to predict the stock industry sector listed on the Indonesia Stock Exchange (BEI) based on financial reports using the Random Forest method. The dataset used in this research includes financial data from companies listed on the IDX in the period 2010 to 2022. The data processing process includes data cleaning, handling class imbalance with oversampling techniques using SMOTE, and feature scaling using StandardScaler. The Random Forest model is used to classify companies into appropriate industry sectors. The eval_uation results show that the model has good performance with an overall accuracy of 80.21%. Several classes showed very good performance, such as the Financials class with precision of 95.24%, recall of 100%, and F-1 score of 97.56%. However, there are also classes that show lower performance, such as the Healthcare class with a precision of 51.61% and an F-1 score of 61.54%. The confusion matrix indicates that the model is able to identify most classes accurately, although there are several classes with prediction errors.

Downloads

Published

2024-10-25

How to Cite

Zhafran, I. K. E., & Saepudin, D. . (2024). Prediction of Stock Industry Sectors Listed on the Indonesia Stock Exchange (IDX) based on Financial Statements with the Random Forest Method. Jurnal Indonesia Sosial Teknologi, 5(10), 4189–4202. https://doi.org/10.59141/jist.v5i10.1239