Recommendation System Using Autoencoders

Diana Ferreira,Sofia Silva,José Machado,António Abelha

doi:10.3390/app10165510

Abstract

The magnitude of the daily explosion of high volumes of data has led to the emergence of the Big Data paradigm. The ever-increasing amount of information available on the Internet makes it increasingly difficult for individuals to find what they need quickly and easily. Recommendation systems have appeared as a solution to overcome this problem. Collaborative filtering is widely used in this type of systems, but high dimensions and data sparsity are always a main problem. With the idea of deep learning gaining more importance, several works have emerged to improve this type of filtering. In this article, a product recommendation system is proposed where an autoencoder based on a collaborative filtering method is employed. A comparison of this model with the Singular Value Decomposition is made and presented in the results section. Our experiment shows a very low Root Mean Squared Error (RMSE) value, considering that the recommendations presented to the users are in line with their interests and are not affected by the data sparsity problem as the datasets are very sparse, 0.996. The results are quite promising achieving an RMSE value of 0.029 in the first dataset and 0.010 in the second one.

Highlights

The past few years have been decisive for the foundation of a new global era, being especially notorious the impact of a diverse set of forces and trends associated with the acceleration of scientific and technological discoveries in the field of information
The flourishing of the Information Age promotes the momentum of the Internet of Things (IoT), which entails an environment pervaded by vast amounts of intelligent devices capable of sensing, capturing, computing and operating the real world [1]
Retail organisations are under constant pressure to find new ways to respond to the progressive changes in the marketplace while at the same time meeting the increasingly challenging needs of their customers

Summary

Introduction

The past few years have been decisive for the foundation of a new global era, being especially notorious the impact of a diverse set of forces and trends associated with the acceleration of scientific and technological discoveries in the field of information. The flourishing of the Information Age promotes the momentum of the Internet of Things (IoT), which entails an environment pervaded by vast amounts of intelligent devices capable of sensing, capturing, computing and operating the real world [1]. Everyday, these devices generate continuous streams of real-time data. There is a large amount of data being produced and disseminated throughout the world on a daily basis This vast amount of data may appear to be meaningful in decision-making processes, in reality, people are overwhelmed by this continuous flow of data [2,3]. With the evolution of technology and the exponential growth of information available, the population is starting to struggle to find what they need or prefer

Objectives

Methods

Results

Conclusion