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