A Modified WASPAS Method for the Evaluation of E-Commerce Websites Based on Pythagorean Fuzzy Information

Web and business e-commerce site assessment is the act of comparing e-commerce sites based on their functionality, efficiency, or ability to meet the needs of a business or its clients. They are essential to keep up with the market changes and shifts to provide better compliance with security requirements and to optimize the interface to hold onto user attention. The modified versions of the WASPAS method hybrid with Pythagorean fuzzy sets are exploited to evaluate the e-commerce websites like the Amazon review dataset, Chnsenti Corp., and IMDB dataset using various performance indicators. The WASPAS model with balancing factor $\beta =\exp \,(j)$ demonstrates an average accuracy of 94.01% for the Amazon review dataset, 98.19% for the Chnsenti Corp. dataset, and 98.83% in the case of the IMBD dataset with a mean execution time of 806.60 sec, 787.10 sec and 809.19 sec, respectively. The proposed model is compared with reported state of art results methods SVM, SVM hybrid with unigram, SVM hybrid with unigram, SVM hybrid with unigram & grid search techniques, XGBoost and ERF-XGB methods with their accuracy of 50.40%, 80.81%, 80.81%, 90.1 and 98.2, respectively. The global fitness value and mean execution time from 50 independent runs are calculated for these datasets, and statistical indicators are used to see the stability of the study. The proposed approach significantly enhanced performance and reduced computational complexity, making it a promising tool for real-time detection and prediction of the efficiency of employees in various organizations and a tool for growth.