Deep Based Recommender System For Relevant K Pick-up Points

Abstract

Recommender Systems are software tools used to generate and provide suggestions for items and other entities to the users by exploiting various strategies. They are widely used and influence the daily life of almost everyone in different domains like e-commerce, social media, entertainment, or transportation in the mobility industry. The efficient generation of relevant recommendations in large-scale systems is a very complex task. This paper describes a deep recommender system for the most relevant K pick-up points for a driver. It is based on spatiotemporal features, points of interest (i.e POIs) and weather data using deep neural networks. Putting through a test with various features sets, we were able to achieve positive results. The effictiveness of our approach is demonstrated by the results, achieving a low loss value in most cases.