Sistema Recomendador de prescripciones médicas basado en clusterización.

Abstract

Abstract: Recommender systems are currently defined as a branch of research in the area of Machine Learning. The main idea of a recommender system is to build a relationship between items, users and make the decision to select the most suitable item for the specific user; there are four main ways in which they produce their suggestions for the user: content-based, collaborative, demographic and hybrid filtering. Recommender systems employ diverse sources of information to provide users with product predictions and recommendations, balancing between variables such as accuracy, novelty and dispersion in recommendations. The present degree work starts with the state of the art of recommender systems, focusing in depth on concepts, classifications and approach related to information. Subsequently, a data set of diabetic patients is selected, which is analyzed, a data treatment and cleaning is developed to then implement a recommender system in the health area using various clustering algorithms, and finally the evaluation process of the recommendations.