LAUSR

Online social databases are rich sources to retrieve appropriate information that is subsequently analyzed for forthcoming trends prediction. In this paper, we identify rising stars in cricket domain by employing machine learning techniques. More precisely, we predict rising stars from batting as well as from bowling realms. For this intent, the concepts of co-players, team, and opposite teams are incorporated and distinct features along with their mathematical formulations are presented. For classification purpose, generative and discriminative machine learning algorithms are employed, and two models from each category are evaluated. As a proof of applicability, the proposed approach is validated experimentally while analyzing the impact of individual features. Besides, model and categorywise assessment is also performed. Employing cross validation, we demonstrate high accuracy for rising star prediction that is both robust and statistically significant. Finally, ranking lists of top ten rising cricketers based on weighted average, performance evolution, and rising star scores are compared with the international cricket council rankings.