An integrated model for evaluation of big data challenges and analytical methods in recommender systems

Document Type

Article

Publication Date

1-31-2022

Abstract

The study aimed to present an integrated model for evaluation of big data (BD) challenges and analytical methods in recommender systems (RSs). The proposed model used fuzzy multi-criteria decision making (MCDM) which is a human judgment-based method for weighting of RSs' properties. Human judgment is associated with uncertainty and gray information. We used fuzzy techniques to integrate, summarize, and calculate quality value judgment distances. Then, two fuzzy inference systems (FIS) are implemented for scoring BD challenges and data analytical methods in different RSs. In experimental testing of the proposed model, A correlation coefficient (CC) analysis is conducted to test the relationship between a BD challenge evaluation for a collaborative filtering-based RS and the results of fuzzy inference systems. The result shows the ability of the proposed model to evaluate the BD properties in RSs. Future studies may improve FIS by providing rules for evaluating BD tools.

Keywords

Recommender system properties, Big Data properties, Dig Data challenges, Analytical methods, Fuzzy multi-criteria decision making, Fuzzy AHP, Fuzzy inference system, Privacy

Divisions

Software,fac_law

Funders

National Research, Development and Innovation Fund of Hungary [TKP2020-NKA-02]

Publication Title

Journal of Big Data

Volume

9

Issue

1

Publisher

SpringerOpen

Publisher Location

CAMPUS, 4 CRINAN ST, LONDON, N1 9XW, ENGLAND

This document is currently not available here.

Share

COinS