Using Machine Learning in Hybrid Recommendation System for Diet Improvement Based on Health and Taste
Using Machine Learning in Hybrid Recommendation System for Diet Improvement Based on Health and Taste
Abstract
Recommendation systems are used everywhere today, such as for online shopping or Netflix videos. The use of these systems necessitates the ability to predict the taste of food effectively. In addition, other food concerns, such as food safety and nutritional value have become more important than before. With these thoughts, a novel diet improvement system, which is based on a recommendation system using hybrid matrix decomposition and K-nearest neighborhood algorithms, is proposed in this paper. The need to minimize the error of prediction in terms of taste and obtain a healthier prediction, required the evaluation of a combination of different algorithms and also required different components of algorithms to be changed to determine the most accurate way of improving the diet. The results of an additional psychological study on induced motivation were incorporated into the system to develop a method to generate a model for each user to enable them to make the transition from tasty food to tasty and healthy food. The system contributes a new hybrid optimized recommendation system based on novel system construction.