Forecasting Monthly Hotel Occupancy Data (2021–2025) by using ARIMA Model
DOI:
https://doi.org/10.33021/nvfgpb79Abstrak
Hotel room occupancy forecasting plays a crucial role in the hospitality industry, supporting operational planning, revenue management, and strategic decision-making. This study applies the Autoregressive Integrated Moving Average (ARIMA) model to forecast the monthly star hotel occupancy rate in Indonesia from 2021 to 2025 using data obtained from Badan Pusat Statistik (BPS). Following the Box-Jenkins methodology, the analysis includes stationarity testing using the Augmented Dickey-Fuller (ADF) test, model identification via ACF and PACF plots, parameter estimation, and residual diagnostics with the Shapiro-Wilk and Ljung-Box tests. Among 25 candidate models, ARIMA(0,1,4) was selected based on diagnostic compliance and the lowest forecasting errors. The model achieved a Mean Absolute Percentage Error (MAPE) of 7.33%, a Mean Squared Error (MSE) of 24.9996, a Root Mean Squared Error (RMSE) of 4.9999, and a Mean Absolute Error (MAE) of 3.0616, classifying the forecast as highly accurate according to the Lewis (1982) criterion. Forecasts for the remaining months of 2025 are presented with 95% confidence intervals. The results confirm that the ARIMA model remains a reliable, transparent, and statistically adequate method for short-term hotel occupancy forecasting.
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 Hana Arabella Liliana Sigalingging

Artikel ini berlisensi Creative Commons Attribution 4.0 International License.