Sales prediction of religious product and services of Mutawwif Haramain Travel & Tours using predictive analytics

Sales prediction in the religious services sector is challenging due to seasonal, cultural, and economic factors, which make traditional methods less reliable. This research develops a predictive model for sales prediction at Mutawwif Haramain Travel & Tours, utilizing machine learning algorithms, specifically Decision Tree, Random Forest, and Naive Bayes, to uncover patterns in customer behavior and seasonal demand. Following the CRISP-DM methodology, data from January to December 2024 was collected, covering factors such as product sales, customer demographics, and seasonal events. The Decision Tree algorithm was selected for its highest accuracy of 89.29%, reflecting its ability to accurately classify sales outcomes compared to the other models. The final model was deployed in an interactive dashboard, providing real-time insights to aid decision-making, resource optimization, and marketing strategies. The model is scalable for future growth at MHTT and can be applied to other sectors. Future improvements will include adding more environmental and customer-related variables to enhance accuracy and adaptability in a dynamic market.