Penerapan Data Mining pada Algoritma Multiple Linear Regression dalam Peramalan Harga Emas

Dina, Intan Rachma
Barata, Mula Agung
Yuwita, Pelangi Eka

SMARTICS Journal
Vol 11 No 1 (2025): SMARTICS Journal (April 2025)

Gold, a precious metal, is highly favored for its ease of maintenance and low risk of loss, making it a popular investment choice. However, gold prices are subject to fluctuations influenced by factors such as the dollar exchange rate, market demand and supply, and monetary crises. Understanding these fluctuations is crucial for investors to minimize losses and maximize profits. The dataset, sourced from Investing.Com, spans from January 2019 to December 2024 and includes 1548 records with five attributes. The error rate was evaluated using Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). This study aims to forecast gold prices using the Multiple Linear Regression algorithm, with the K-Fold Cross Validation method applied to enhance model accuracy. The results show RMSE and MAPE values of 695.7909 and 0.27%, respectively, indicating that the Multiple Linear Regression algorithm is effective in predicting gold prices.