Year: 2024
Type: book-chapter
Abstract: Recommendation systems represent complex algorithms that direct the user to interesting resources within the vast data space available on the Internet, taking into account his personal information, preferences, etc. Machine learning and multi-criteria methods have brought about significant development in recommendation systems, providing personalized and accurate solutions for recommending products or services, etc.However, the problem that machine learning models face is that they tend to lack robustness and accuracy if they lack features that help personalize recommendations.In this paper, we address this problem by proposing a new system known as ML-TOPSIS (Machine Learning and Preference Ranking Technique by Similarity to Ideal Solution) for personalized restaurant recommendations based on health, location, and ratings.The primary goal of this system is to develop an application that attempts to provide food from restaurants that matches a person's health status using the multi-criteria TOPSIS method, as well as their geographic location and similar ratings using machine learning algorithms based on collaborative filtering.By considering the nutritional requirements of individuals, especially for individuals suffering from obesity and diabetes.The results of the proposed system show that it helps users find restaurants according to their needs and aspirations to provide better suggestions.
Institution: University of Guelma
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4402009448