This repository presents the results obtained during the Master’s Thesis and months of internship at Universidad Autónoma de Madrid, a Spanish public university, established in 1968. The main focus of this work is to provide a scientific analysis and a description of the implementation realized to develop a Recommender System using Graph Neural Networks. After analyzing the state of the art for traditional recommendation systems as well as the potential of Graph Neural Networks (GNN), such as GraphSAGE, the following thesis focuses on the hybrid recommendation system that employs GNN, which has piqued the interest of researchers because it promises to address some problems by augmenting existing information with graphs. This Master's Thesis describes an architecture for tackling the recommendation issue for the Point of Interest, which uses the Heterogeneous graph to characterize the data supplied to the system.
- Download the Yelp Dataset - https://www.yelp.com/dataset
- Yelp Data Analysis: Notebook containing the analysis and study of the entire Yelp dataset, up to the extraction of a subset of data.
- Model_V2_Regression/Model_V2_Classification/Model_V2_Classification_Hyperparameter: Notebooks containing all the operations described in the thesis work, divided into Regression and Classification Tasks.