Particle swarm optimization based method for personalized menu recommendations

Abstract

This paper presents a Particle Swarm Optimization (PSO) based method forgenerating healthy daily menu recommendations for elder. In order to apply the PSO method to the case of generating menu recommendations, we have redefined the concepts of particle, position and velocity of the particle, as well as the formulae for updating the position and velocity of the particle. Additionally, to evaluate the quality of a particle (i.e. a solution), we have used a fitness function that has four components: the closeness to a nutritionist dietary recommendation, a price component, a delivery time component, and a diversity component that estimates of how diverse a daily recommendation is. The method proposed has been tested on a set of different user profiles.