Comparison Random Forest Regression and Linear Regression For Forecasting BBCA Stock Price

Authors

  • Arif Mudi Priyatno Universitas Pahlawan Tuanku Tambusai
  • Lailatul Syifa Tanjung Universitas Pahlawan Tuanku Tambusai
  • Wahyu Febri Ramadhan Universitas Pahlawan Tuanku Tambusai
  • Putri Cholidhazia Universitas Pahlawan Tuanku Tambusai
  • Putri Zulia Jati Universitas Pahlawan Tuanku Tambusai
  • Fahmi Iqbal Firmananda Universitas Pahlawan Tuanku Tambusai

DOI:

https://doi.org/10.31004/jutin.v6i3.16933

Abstract

Stock trading is a popular financial instrument worldwide. In Indonesia, the stock market is known as the Indonesia Stock Exchange (BEI), and one actively traded stock is PT Bank Central Asia (BBCA). However, predicting stock price movements is challenging due to various influencing factors. Investors use fundamental and technical analyses for decision-making, but results often vary. Machine learning, particularly random forest regression and linear regression algorithms, can be used for stock price forecasting. In this paper, we compares these two machine learning methods to forecast BBCA stock prices, aiming to provide more accurate and effective solutions for investor's investment and trading decisions. The evaluation results of cross-validation mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) for linear regression were 0.12848, 0.35807, 0.29570, and 0.0036%, respectively, while for random forest regression were 27473.76, 158.04, 142.70, and 1.7153%. These findings indicate that linear regression outperforms in forecasting performance.

Downloads

Published

2023-07-28

How to Cite

Priyatno, A. M., Tanjung, L. S., Ramadhan, W. F., Cholidhazia, P., Jati, P. Z. ., & Firmananda, F. I. (2023). Comparison Random Forest Regression and Linear Regression For Forecasting BBCA Stock Price. Jurnal Teknik Industri Terintegrasi (JUTIN), 6(3), 718–732. https://doi.org/10.31004/jutin.v6i3.16933

Issue

Section

Articles of Research

Most read articles by the same author(s)