FeastFlow: Python-Driven Restaurant Recommendations at Your Fingertips

Abstract

This research paper explores the development of a Restaurant Recommendation System using Python. Motivated by the challenges users face in selecting suitable dining establishments, the study employs collaborative filtering algorithms for personalized suggestions. Leveraging Python libraries such as Surprise and scikit-learn, the system is implemented, with a focus on data preprocessing, algorithm selection, and code walkthrough. Evaluation metrics, including RMSE, assess system accuracy, while user satisfaction surveys provide qualitative insights. Results demonstrate the system's efficacy, comparing favourably with existing models. The research concludes with reflections on achievements, limitations, and avenues for future enhancement in the dynamic realm of restaurant recommendation systems.