<![CDATA[Indonesia has a high level of vulnerability to tsunami disasters due to seismic activity in subduction zones. This condition requires a fast and accurate tsunami potential prediction system to support effective disaster mitigation. This study aims to compare the performance of five machine learning algorithms in predicting tsunami potential along the West Coast of Lampung, namely Random Forest, K-Nearest Neighbor, Naïve Bayes, Neural Network, and Decision Tree. The dataset consists of 352 earthquake records from 2023–2024 obtained from BMKG, using parameters such as magnitude, depth, and epicentral distance. Model evaluation was conducted using a Confusion Matrix with performance metrics including accuracy, precision, recall, and F1-score. The results indicate that the Random Forest algorithm achieved the best performance with an accuracy of 100% and balanced precision, recall, and F1-score values. These findings are expected to support the development of a machine learning-based tsunami early warning system that is adaptive to local geophysical characteristics.Keywords: Earthquake; Machine Learning; Random Forest; Tsunami prediction AbstrakIndonesia memiliki tingkat kerentanan yang tinggi terhadap bencana tsunami akibat aktivitas gempa bumi di zona subduksi. Kondisi ini menuntut tersedianya sistem prediksi potensi tsunami yang cepat dan akurat untuk mendukung mitigasi bencana. Penelitian ini bertujuan membandingkan kinerja lima algoritma machine learning dalam memprediksi potensi tsunami di Pesisir Barat Lampung, yaitu Random Forest, K-Nearest Neighbor, Naïve Bayes, Neural Network, dan Decision Tree. Data yang digunakan berupa 352 catatan gempa bumi periode 2023–2024 yang bersumber dari BMKG dengan parameter magnitudo, kedalaman, dan jarak episentrum. Evaluasi model dilakukan menggunakan Confusion Matrix dengan metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa algoritma Random Forest memberikan performa terbaik dengan tingkat akurasi 100% serta keseimbangan nilai presisi, recall, dan F1-score. Temuan ini diharapkan dapat mendukung pengembangan sistem peringatan dini tsunami berbasis machine learning yang adaptif terhadap karakteristik geofisika lokal. ]]>
