Open Access. Powered by Scholars. Published by Universities.®
Physical Sciences and Mathematics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Physical Sciences and Mathematics
Evaluation And Assessment Of Recommenders Using Monte Carlo Simulation, Renato Costa, Luiz Fernando Capretz
Evaluation And Assessment Of Recommenders Using Monte Carlo Simulation, Renato Costa, Luiz Fernando Capretz
Electrical and Computer Engineering Publications
There have been various definitions, representations and derivations of trust in the context of recommender systems. This article presents a recommender predictive model based on collaborative filtering techniques that incorporate a fuzzy-driven quantifier, which includes two upmost relevant social phenomena parameters to address the vagueness inherent in the assessment of trust in social networks relationships. An experimental evaluation procedure utilizing a case study is conducted to analyze the overall predictive accuracy. These results show that the proposed methodology improves the performance of classical recommender approaches. Possible extensions are then outlined.
A Fuzzy-Based Inference Mechanism Of Trust For Improved Social Recommenders, Renato Costa, Luiz Fernando Capretz
A Fuzzy-Based Inference Mechanism Of Trust For Improved Social Recommenders, Renato Costa, Luiz Fernando Capretz
Electrical and Computer Engineering Publications
This paper presents a stochastic model based on Monte Carlo simulation techniques for measuring the performance of recommenders. A general procedure to assess the accuracy of recommendation predictions is presented and implemented in a typical case study where input parameters are treated as random values and recommender errors are estimated using sensitive analysis. The results obtained are presented and a new perspective to the evaluation and assessment of recommender systems is discussed.