A Hybrid Ontology-Based Recommendation System in e-Commerce

Márcio Guia,Jorge Bernardino,Rodrigo Rocha Silva

doi:10.3390/a12110239

Abstract

The growth of the Internet has increased the amount of data and information available to any person at any time. Recommendation Systems help users find the items that meet their preferences, among the large number of items available. Techniques such as collaborative filtering and content-based recommenders have played an important role in the implementation of recommendation systems. In the last few years, other techniques, such as, ontology-based recommenders, have gained significance when reffering better active user recommendations; however, building an ontology-based recommender is an expensive process, which requires considerable skills in Knowledge Engineering. This paper presents a new hybrid approach that combines the simplicity of collaborative filtering with the efficiency of the ontology-based recommenders. The experimental evaluation demonstrates that the proposed approach presents higher quality recommendations when compared to collaborative filtering. The main improvement is verified on the results regarding the products, which, in spite of belonging to unknown categories to the users, still match their preferences and become recommended.

Highlights

Over the last years, due to the growth of the Internet, the amount of data found in web pages and social networks has increased significantly
The main contributions of this work are the following: We propose a new e-commerce recommendation system, which combines collaborative filtering with ontology-based recommenders; The proposed recommendation system considers the users with similar preferences to the active user and obtains knowledge about the user, their neighbours, products and the relationship between them; Our proposal increases the number of recommended products from categories which the active user has not yet purchased; The proposed system is scalable, which means that it maintains good level performance when the workload increases
In order to perform the evaluation of our work, we compare the hybrid ontology-based recommendation system that we propose in this paper, to a collaborative filtering approach, which means that in the second one, we apply the K-Nearest Neighbor algorithm (KNN) algorithm to Neighbours and Products

Summary

Introduction

Due to the growth of the Internet, the amount of data found in web pages and social networks has increased significantly. The growth of the Internet has potentiated the proliferation of e-services over numerous online platforms, whose main advantage is to provide products and services anywhere and anytime to users who have not yet purchased them [2]. With this amount of data and services available, it is difficult for users to quickly find items in which they are interested in, and for e-commerce and similar systems to recommend items among the available data. One of the most common successful methods in recommendation systems is collaborative filtering [3], which consists of recommending products and items that have similar preferences among users to the active user who liked or purchased them in the past

Objectives

Findings

Discussion

Conclusion