<![CDATA[Accurate forecasting of hotel booking demand is essential for resource optimization, revenue maximization, and enhanced customer experience in the hospitality industry. This study evaluates the performance of three forecasting models, ARIMA, Prophet, and LSTM, using historical booking data to identify the most effective approach for predicting demand. The evaluation employed four key metrics: Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and R-squared (R²), providing a comprehensive comparison. The results indicate that the LSTM model outperformed the others in prediction accuracy, achieving the lowest MAE (2.71) and MAPE (21.33%), demonstrating its strength in capturing complex patterns. However, its negative R-squared value (-0.20) suggests limitations in explaining overall data variance compared to ARIMA (0.51) and Prophet (0.50). The Prophet model excelled in seasonal decomposition but showed the highest MAPE (71.86%), while ARIMA delivered robust residual diagnostics, adhering well to model assumptions with consistent variance and randomness in residuals. The findings suggest that while LSTM is most effective for short-term forecasting, ARIMA and Prophet provide better interpretability and reliability for long-term trend analysis. A hybrid approach combining the strengths of all three models is recommended to enhance predictive accuracy and robustness. This study provides actionable insights for industry stakeholders seeking to improve decision-making processes and operational efficiency through advanced forecasting techniques.]]>
Copyrights © 2025
