Integrating Context and Criteria in Hotel Recommendations: A Deep Learning Perspective

Recommendation systems are widely utilized to personalize user experiences by sorting and providing information based on user preferences. Multi-Criteria Recommendation Systems (MCRs) enhance basic recommendation systems by considering user ratings and interactions across various criteria. When contextual information is also integrated, these systems become Context-Aware Multi-Criteria Recommendation Systems (CA-MCRs). This paper explores the use of Deep Neural Networks (DNN) in CA-MCRs for making predictions. The incorporation of deep learning in recommendation systems is relatively new and offers higher accuracy compared to traditional methods, as evaluated by RMSE and MAE scores. Deep Neural Networks (DNNs) facilitate efficient feature extraction through embedding layers, eliminating the need for manual intervention. The model is tested on TripAdvisor data, which includes multi-criteria ratings of various hotels. Our approach proved its supremacy by demonstrating the efficacy of deep learning in enhancing recommendation accuracy.