@article{Yuniarto_Hariguna_Nawangnugraeni_2025, place={Purwokerto}, title={Comparison of Accuracy and Computation Time for Predicting Earthquake Magnitude in Java Island}, volume={6}, url={https://jutif.if.unsoed.ac.id/index.php/jurnal/article/view/5044}, DOI={10.52436/1.jutif.2025.6.4.5044}, abstractNote={<p>Java Island has numerous active faults, making earthquake magnitude prediction a crucial component of disaster mitigation efforts. This study conducted a rigorous comparative analysis of four machine learning algorithms—Random Forest, Neural Network, Linear Regression, and Support Vector Machine—to determine their effectiveness in this specific task. The methodology employed involved systematic hyperparameter optimization for each model to ensure a fair and robust evaluation, with performance measured by Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and training time. The results showed that all three nonlinear models significantly outperformed Linear Regression. Random Forest achieved the highest accuracy (RMSE 0.5445), but Support Vector Machine and Neural Network demonstrated very competitive and nearly equal performance. The study concluded that while Random Forest has a slight advantage, several state-of-the-art models are highly capable of addressing this problem after appropriate optimization. This underscores the critical role of methodical tuning and implies that model selection in practical applications depends on a trade-off between modest improvements in accuracy and computational efficiency.</p>}, number={4}, journal={Jurnal Teknik Informatika (Jutif)}, author={Yuniarto, Abdul Hakim Prima and Hariguna, Taqwa and Nawangnugraeni, Devi Astri}, year={2025}, month={Sep.}, pages={2811–2824} }