This project explores the impact of culinary diversity on the effectiveness of different recommender systems. Using datasets representing various states' gastronomy offers, we examine how cuisine variety affects the performance of collaborative filtering systems, specifically focusing on KNN and SVD algorithms.

The project aims to understand the influence of diverse and less diverse culinary environments on recommendation accuracy. We test an hypothesis on cosine similarity measures and do root mean square error (RMSE) evaluations, so we can compare the prediction effectiveness of KNN and SVD algorithms in both high-diversity and low-diversity gastronomy subsets.

• Python 3.x
• Libraries: scikit-learn, surprise, pandas, numpy and more
• Jupyter Notebook for .ipynb file execution