Alfian Ramadhan
Universitas Amikom Yogyakarta

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Stock Price Prediction Using SVR: A Feature Engineering and Hyperparameter Tuning Approach Alfian Ramadhan; Yoga Pristyanto; Anggit Dwi Hartanto; Donni Prabowo
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): Juni 2026 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.7249

Abstract

Stock price prediction in Indonesia's volatile mining sector poses significant forecasting challenges driven by commodity price dynamics and structural market shifts. This study proposes a systematic prediction framework for PT Indo Tambangraya Megah Tbk (ITMG.JK) integrating technical and market-derived non-technical feature engineering, LightGBM-based feature selection, multilevel TimeSeriesSplit cross-validation, and hyperparameter optimization. Support Vector Regression (SVR) is benchmarked against LightGBM, XGBoost, and Random Forest under 5-fold, 10-fold, and 15-fold schemes. SVR achieves the best performance at 10-fold, with RMSE of 0.0121, MAE of 0.0090, MAPE of 1.1457%, and R² of 0.9249. Generalization experiments across four additional stocks in banking, automotive, and mining sectors confirm SVR's robustness, maintaining R² above 0.89 and MAPE below 2.65% in all cases while tree-based models produce negative R² on certain datasets. Statistical validation via Wilcoxon signed-rank test (p < 0.05) and Cohen's d (|d| > 0.8) confirms the significance of SVR's advantage. These findings indicate that SVR consistently outperforms the evaluated models under the proposed experimental framework.