Prediksi Trend Harga Saham Jangka Pendek berdasarkan Fitur Technical Analysis dengan menggunakan Algoritma Random Forest

Michael Eggi Bastian (Fakultas Ilmu Komputer, Universitas Brawijaya)
Bayu Rahayudi (Fakultas Ilmu Komputer, Universitas Brawijaya)
Dian Eka Ratnawati (Fakultas Ilmu Komputer, Universitas Brawijaya)

Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 5 No 10 (2021): Oktober 2021

Stock trading is a daily activity carried out by a stock trader. A stock trader can perform this trading activity on a capital market. In the capital market, you can see a chart that depicts the price movement of a stock in a certain period, also known as "Price Trend". The most important characteristic of a price trend is volatile and irregular changes in direction. Due to its volatile and irregular nature, a problem arises in knowing where the price trend will move. Any mistake in predicting the direction of the trend can cause losses. This study implements the random forest algorithm as a solution model, and technical analysis as a predictive feature to minimize errors in predicting future stock price trends. Based on the test results, the combination of the random forest algorithm and technical analysis is able to minimize errors in predicting price trends with an accuracy of 84% and an f1 score of 88%.