Quantitative Assessment of Player Performance and Winner Prediction in ODI Cricket

The statistics of professional sports, including players and teams, provide numerous opportunities for research. Cricket is one of the most popular team sports, with billions of fans all over the world. In this thesis, we address two problems related to the One Day International (ODI) format of the game. First, we propose a novel method to predict the winner of ODI cricket matches using a team-composition based approach at the start of the match. Second, we present a method to quantitatively assess the performances of individual players in a match of ODI cricket which incorporates the game situations under which the players performed. The player performances are further used to predict the player of the match award. Players are the fundamental unit of a team. Players of one team work against the players of the opponent team in order to win a match. The strengths and abilities of the players of a team play a key role in deciding the outcome of a match. However, a team changes its composition depending on the match conditions, venue, and opponent team, etc. Therefore, we propose a novel dynamic approach which takes into account the varying strengths of the individual players and reflects the changes in player combinations over time. Our work suggests that the relative team strength between the competing teams forms a distinctive feature for predicting the winner. Modeling the team strength boils down to modeling individual players’ batting and bowling performances, forming the basis of our approach. We use career statistics as well as the recent performances of a player to model him. Using the relative strength of one team versus the other, along with two player-independent features, namely, the toss outcome and the venue of the match, we evaluate multiple supervised machine learning algorithms to predict the winner of the match. We show that, for our approach, the k-Nearest Neighbor (kNN) algorithm yields better results as compared to other classifiers. Players have multiple roles in a game of cricket, predominantly as batsmen and bowlers. Over the generations, statistics such as batting and bowling averages, and strike and economy rates have been used to judge the performance of individual players. These measures, however, do not take into consideration the context of the game in which a player performed across the course of a match. Further, these types of statistics are incapable of comparing the performance of players across different roles. Therefore, we present an approach to quantitatively assess the performances of individual players in a single match of ODI cricket. We have developed a new measure, called the Work Index, which represents the amount of work that is yet to be done by a team to achieve its target. Our approach incorporates game situations and the team strengths to measure the player contributions. This not only helps us in