SVMCTI: Support Vector Machine-based Cricket Talent Identification Model

Abstract

Recognizing sports talent is one of the intensively discussed topics in this day and age. Cricket is a sport of keen interest and has fascinated researchers all over the world to ponder and work in this domain. In this era of technological competence, incorporating technology in cricket talent identification is an incumbent task. Also, early-age talent identification is considered to be more beneficial as instead of wasting time and other resources on random performers, we can limit the training and spending on the talented performers that could yield better results. In this article, a machine learning-based approach is proposed for Cricket Talent Identification using SVM (RBF kernel) to classify a dataset of performers into talented performers (possessing cricketing talent) and non-talented performers (not possessing cricketing talent). The dataset has been collected from early-age performers taking into consideration the benefits of talent identification at early ages. The data have been gathered concerning various physical/motor, anthropometric, and cognitive abilities. Using the feature selection technique, the best-contributing parameters were determined and supplied to the model. After performing experimentation, the results were evaluated based on various evaluation metrics like Accuracy, precision, and f1-Score. we achieved an accuracy score of 96.42%, a precision of 0.94, and an f1_score of 0.96. The results obtained have been cross-validated using the 10-cross validation technique.