Application of Fuzzy Inference System Sugeno Model for Forecasting Antam Gold Prices in Indonesia: A Case Study of Monthly Data 2023–2025

Irwanda Syahputra (Universitas Samudra)
Alfa Saleh (Universitas Samudra)
Khairul Anam (Universitas Samudra)

Sisfo: Jurnal Ilmiah Sistem Informasi
Vol. 10 No. 1 (2026): Sisfo: Jurnal Ilmiah Sistem Informasi, Mei 2026

Antam gold prices represent one of the most volatile investment indicators in Indonesia, influenced by macroeconomic factors including rupiah exchange rates, global inflation, and geopolitical uncertainty. The ability to accurately forecast gold prices has become a strategic necessity for investors and market participants. This study applies a Fuzzy Inference System (FIS) with the Sugeno model to forecast Antam gold prices using monthly data from January 2023 to December 2025, comprising 36 data points. The input variables are gold prices from the previous month (t-1) and two months prior (t-2), while the output variable is the predicted price for period t. Data is split 75:25 for training and testing. Evaluation using Mean Absolute Percentage Error (MAPE) yields 2.14%, categorized as excellent accuracy. This study provides empirical evidence that the simple yet interpretable Fuzzy Sugeno method achieves high accuracy in commodity price time series forecasting.