Abstract:

The fast evolution of artificial intelligence (AI) has transformed the food service industry, allowing for extreme personalization of the customer experience. The proposed research develops a Hybrid AI-based menu recommendation system that provides customers with personalized food recommendations based on the analysis of extensive customer data, including preferences, dietary limitations, past purchases, and current situational variables. The approach uses a stack of machine learning models, natural language processing (NLP), and predictive analytics. The system is a hybrid of content-based filtering and collaborative filtering, with sentiment analysis of textual feedback to optimize preference scores. A dynamic adaptive learning process, informed by continuously changing customer behavior patterns and tastes, will provide recommendations based on continuous feedback. With the introduction of this intelligent system, user satisfaction has increased significantly, and restaurants' operational efficiency has improved. The results show that applying AI-based personalization not only increases customer engagement but also provides valuable insights for better menu design, leading to a tangible decrease in food waste and reinforcing business competitiveness. This study confirms the potential of smart recommenders to transform and streamline the current food service business, a large-scale approach to making informed decisions in the transforming food industry.