Cricket Squad Formation using Machine Learning

Abstract

Cricket is primarily played in three formats around the world: test match, one- day international (ODI), and twenty-twenty (T20). T20 has made a great revolution in the world of cricket. The Pakistan Cricket Board (PCB) arranges a tournament named the Pakistan Super League (PSL) every year, which is in T20 format. PSL is liked and watched by a large number of people, and it has a greater amount of statistical data. PSL is based on the Draft system for selecting players for making teams. This draft-based method for selecting players has different categories, each with its own constraints. 16 player squad must have five foreign players, and an 18 players squad could have six or five foreign players. A larger amount of money is used in the draft system. Players’ selection is one of the most important tasks for team formation. PSL team selection is made by team management, and it is very complex for humans to analyze all the previous statistics of the players for better selection. It is also true that human-based systems are not very efficient. It is very important to analyze players' performances for ease of selection and to make the right decision for the selection of players for teams by team management, coaches, and captains. In this thesis, machine learning techniques are used for squad selection in our model, which is named SFPML (Squad Formation in Pakistan Super League using Machine Learning). Important features of a batsman and bowler are used. Our model ranks the batsmen and bowlers based on their previous performances. If a new player enters the PSL tournament, his position in the league is determined by finding similarities among PSL players. Our thesis also attempts to predict the performances of players, such as how many runs a batsman will score, and how many wickets a bowler will take.