Journal of Informatics, Electrical and Electronics Engineering
Vol. 6 No. 1 (2026): September 2026

Overcoming Tree Extrapolation Limits in Gold Price Forecasting: A Stationary Return-Reconstructed XGBoost Approach

Imam Saputra (Sekolah Tinggi Ilmu Manajemen Sukma Medan, Sumatera Utara)
Zulfikar (Politeknik Kampar, Riau)
Juni Ismail (Politeknik Bisnis Indonesia, Sumatera Utara)
Alfry Aristo Jansen Sinlae (Universitas Katolik Widya Mandira, Nusa Tenggara Timur)
Yanto Saputra (Institut Teknologi Bisnis Riau, Riau)
Raja Anan Nasution (Akademi Manajemen Informatika dan Komputer ITMI, Sumatera Utara)
Elsy Rahajeng (Universitas Islam Negeri Syarif Hidayatullah, Banten)
Mesran (Sekolah Tinggi Ilmu Manajemen Sukma Medan, Sumatera Utara)



Article Info

Publish Date
28 Sep 2026

Abstract

This study addresses the fundamental tree extrapolation limit inherent in gradient-boosted decision tree ensembles when forecasting non-stationary financial time series during historical market rallies. Standard raw-price regression models fail to project unseen price regimes because decision trees assign static scalar predictions to terminal leaf nodes, capping predictions at historical maximums. To overcome this spatial limitation, we propose a Stationary Return-Reconstructed XGBoost framework that shifts the machine learning target from non-stationary spot prices to stationary daily relative returns before deterministically re-integrating predicted returns into nominal price levels. Evaluated on an out-of-sample testing set spanning 2022 to 2024, the return-reconstructed framework completely eliminates flatline prediction plateaus during record-setting gold price rallies exceeding 2,800 USD per troy ounce. The proposed model achieves an R-squared score of 0.9905, a Root Mean Squared Error of 28.17 USD per troy ounce, and a Mean Absolute Percentage Error of 1.12 percent, outperforming the raw-price baseline model by 92.75 percent in average error reduction. Furthermore, game-theoretic SHAP analysis validates that daily return forecasts are driven by macroeconomically sound transmission channels, predominantly led by the US Dollar Index and monthly historical price memory

Copyrights © 2026






Journal Info

Abbrev

jieee

Publisher

Subject

Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering

Description

Fokus kajian Journal of Informatics, Electrical and Electronics Engineering, yaitu: 1. Control System, 2. Artificial Intelligence, 3. Informatics Engineering, 4. Electronics, 5. Advanced energy material, 6. Automatic power control, 7. Battery technology, 8. Distributed generation, 9. Distribution ...