Developing Restaurant Recommendation System with Neural Collaborative Filtering Method
İlham Hüseyinov, Tolga Hamitovalı · Journal of Emerging Technologies and Innovative Research · 2021
Recommendation Systems are designed to provide a personalized product or service to the user. Its purpose is to predict the future actions of users based on their past behavior and make suggestions accordingly. Recent studies have proven that Deep Learning-based collaborative filtering method has a high success rate. However, there is no study on the implementation of this method in restaurant recommendation systems. The goal of this study is to fill this gap. For this purpose, different models were designed using different restaurant datasets and a deep learning-based collaborative filtering algorithm. Using the evaluation criteria of Restaurant Recommendation Systems, the models developed in this study were compared with the results of other studies. The comparison results are presented graphically. As a result, the hyperparameters of the most optimal model based on the Deep Learning-based collaborative filtering algorithm were found.