Innovative Ranking Strategy For IPL Team Formation
Arnabi Mitra1, Saptarshi Banerjee2, Debayan Ganguly3, Ritajit Majumdar4, Kingshuk Chatterjee5
1Arnabi Mitra, Department of Computer Science and Engineering, Government College of Engineering and Leather Technology, Kolkata, India.
2Saptarshi Banerjee, Department of Computer Science and Engineering, Government College of Engineering and Leather Technology, Kolkata, India.
3Debayan Ganguly, Department of Computer Science and Engineering, Government College of Engineering and Leather Technology, Kolkata, India.
4Ritajit Majumdar, Advanced Computing & Microelectronics Unit, Indian Statistical Institute, Kolkata, India.
5Kingshuk Chatterjee, Department of Computer Science and Engineering, Government College of Engineering and Ceramic Technology, Kolkata, India.
Manuscript received on September 19, 2019. | Revised Manuscript received on October 05, 2019. | Manuscript published on October 30, 2019. | PP: 723-728 | Volume-9 Issue-1, October 2019 | Retrieval Number: F9290088619/2019©BEIESP | DOI: 10.35940/ijeat.F9290.109119
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Indian Premier League (IPL) is a tournament of twenty over cricket matches. Teams of this tournament are selected via an auction from a pool of players. Each team employs a think-tank to build the best possible team. Few studies have been performed to automate the process of team selection. However, those studies mostly concentrate either on the current form of the players, or their long term performance. In this paper, we have (i) selected traditional features as well as determined some derived features, which are generated from the traditional features, for batsmen and bowlers, (ii) formulated heuristics for clustering batsmen into openers, middle order batsmen and finishers, (iii) formulated heuristics for relative ranking of batsmen and bowlers considering the current performance as well as the experience of each player, and (iv) have proposed two greedy algorithms for team selection where the total credit point of the team and the number of players in each cluster is fixed. Our proposed ranking scheme and algorithm not only determines the best possible team, but can also determine the best alternate player if one of the target players is unavailable.
Keywords: Heuristic, Ranking, Greedy Algorithm.