Fuzzy optimisation based cricket talent identification

Abstract

In this study, we proposed a cricket talent identification model based on fuzzy optimization that employs the fuzzy analytical hierarchy process (FAHP) and particle swarm optimization (PSO). To evaluate the performance of the model, we used a primary dataset (n = 56) collected from four different schools in J&K UT, India. Our model demonstrated high accuracy, precision, and recall with an accuracy of 92.8%, precision of 96%, and recall of 88%. The model also achieved a low miss rate of 11% and an F1-score of 92.3%. To the best of our knowledge, this is the first attempt to identify cricket talent using this methodology, which overcomes many limitations of conventional AHP-based models. By deriving an exact priority vector from the fuzzy comparison matrix for the criteria, our model eliminates the need for further procedures of defuzzification, making it more efficient and accurate. A comparative analysis of results gained from using Gaussian fuzzy numbers is also provided. Our study demonstrates the feasibility and potential of using fuzzy optimization techniques for cricket talent identification.