Distributed representation of users in recommendation systems

• Grant number: 19/15393-4
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: September 01, 2019
• End date: August 31, 2020
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Tiago Agostinho de Almeida
• Grantee: Bruno Bevilacqua Rizzi
• Host Institution: Centro de Ciências em Gestão e Tecnologia (CCGT). Universidade Federal de São Carlos (UFSCAR). Campus de Sorocaba. Sorocaba , SP, Brazil

Abstract

Currently, there is a growing availability of digital content. With the high amount of information and ease of access, people face an increasing difficulty in finding relevant information. From this problem, recommendation systems were born, which analyze the previous behavior of users to issue personalized recommendations of items. Currently, most companies have some form of recommendation in their channels or services. Still, many problems in the area have not been adequately addressed, one of them being the high dimensionality and sparseness that the current recommendation problems have. Based on this scenario, this project presents a new method whose main objective is to overcome the problem of high dimensionality without compromising performance. The proposed method will be a modification of recent methods of the recommendation area, which, in turn, are inspired by already consolidated methods of the natural language processing area. Its main goal is to make personalized recommendations through a vector representation with reduced dimensionality.