Analisis TPK Hotel serta Wisatawan Menggunakan K-Means dan SARIMA untuk Prediksi Kunjungan Wisata Optimal di Kabupaten Jember

Abstract

This study aims to analyze seasonal tourism activity patterns and predict tourism visit trends in Jember Regency using the K-Means and Seasonal Autoregressive Integrated Moving Average (SARIMA) methods. The problem addressed in this study is the fluctuation of tourist visits and hotel Room Occupancy Rates (TPK), which remain seasonal and have not yet contributed optimally to the regional tourism sector. The data used are secondary data from the 2021–2025 period obtained from the Central Bureau of Statistics (BPS), the Jember Regency Tourism Office, the Jember Regency Transportation Office, and PT KAI DAOP 9 Jember. The main variables include hotel occupancy rates, domestic tourists, and international tourists. The K-Means method was used to classify tourism visit patterns into high season and low season categories, while SARIMA was used to forecast tourism visit trends based on monthly time-series data. The results show that the optimal number of clusters is two clusters with a silhouette score of 0.3982. The high season period predominantly occurs from May to September, while the low season occurs from January to April and October to December. The best models obtained were SARIMA(1,1,2)(0,1,1,12) for hotel occupancy rates and international tourists, and SARIMA(1,2,2)(0,1,1,12) for domestic tourists. The evaluation results show a MAPE value of 8.99% for the hotel occupancy rate variable, indicating that the model can accurately predict hotel occupancy trends. The integration of clustering and forecasting results produced recommendations for optimal tourism visit periods from May to September, which can support tourism strategy planning in Jember Regency.