Optimasi Algoritme Xtreme Gradient Boosting (XGBoost) pada Harga Saham PT. United Tractors Tbk.

Authors

  • Tiyas Astutiningsih Universitas Sebelas Maret
  • Dewi Retno Sari Saputro Universitas Sebelas Maret, Surakarta, Indonesia
  • Sutanto Universitas Sebelas Maret, Surakarta, Indonesia

DOI:

https://doi.org/10.35718/specta.v7i3.1031

Keywords:

Stock Price, Technical Indikator, XGBoost

Abstract

The issue of a recession in 2023 continues to increase, affecting the rise and fall of the stock price index. From
2015 to 2023 the share price of PT. United Tractors Tbk. experiencing fluctuations. The method used to determine
fluctuations in PT. United Tractors Tbk. share data is an ensemble learning. One of the ensemble learning
algorithms that is popular and often used for prediction or classification problems is Extreme Gradient Boosting
(XGBoost). The aim of this research is to obtain the best model ofPT. United Tractors share prices using XGBoost.
XGBoost is a development of Gradient Boosting which has the advantage of faster implementation. The data used
is the share price of PT. United Tractors Tbk. from March 16 2021 to March 31, 2023. This research uses four
technical indicators in analyzing share price movements, namely Exponential Moving Average (EMA), Simple
Moving Average (SMA), Relative Strength Index (RSI) and Moving Average Convergence /Divergence (MACD).
This experiment produced a MAPE value of 3.89%, which shows the optimization of the XGBoost algorithm on
PT share prices. United Tractor Tbk. produces accurate models.

Downloads

Published

2023-12-31

How to Cite

Astutiningsih, T., Saputro, D. R. S., & Sutanto. (2023). Optimasi Algoritme Xtreme Gradient Boosting (XGBoost) pada Harga Saham PT. United Tractors Tbk. SPECTA Journal of Technology, 7(3), 632–641. https://doi.org/10.35718/specta.v7i3.1031

Issue

Vol. 7 No. 3 (2023): SPECTA Journal of Technology

Section

Articles

License

Copyright (c) 2023 Tiyas Astutiningsih

Creative Commons License

This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Attribution-NoDerivs 4.0 Generic(CC BY-ND 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.