In the recent years, Dream 11, a fantasy sports platform has taken the Indian gaming landscape into storm by raking in a valuation of 1 million USD. One of the important aspects of participating in a Dream 11 contest is team selection. Though Dream 11 hosts fantasy Cricket, Kabbadi, Football and Basketball in its platform, Fantasy Cricket has gained more users due to its popularity in India. Moreover, Cricket is one such sport that generates large volumes of data, and therefore provides many opportunities for data analysis. A Dream 11 user needs to select the right mix of players to maximize his/her points, and thereby win some cash rewards. The paper describes a retrospective approach to team selection using the real-world data collected from Player performances in the last 10 matches, to propose a Dream 11 Fantasy team for the upcoming match. The technique used is Integer Programming, implemented using the Gurobi library in Python. The team selection problem has also been analyzed through the lens of Markowitz Optimization, which is mostly used to select stocks in a financial portfolio. The concept of risk aversion has been applied to penalize inconsistent performances, as risk taking and risk averse users might want to bet on different odds for the same match.

Integer Programming, Binary Optimisation, Team Selection, Cricket

[1] Lemmer HH. A measure for the batting performance incricket players.SAfr J Res Sport Phys Educ Recreation26(1):55–64, 2002
[2] Borooah, V. K., and Mangan, J E, “The„Bradman Class?: An Exploration of Some Issues in the Evaluation of Batsmenfor Test Matches, 1877–2006.”, Journal of Quantitative Analysis in Sports, 6 (3), Article 14, 2010.
[3] Kimber, A C and Hansford, A R, “A Statistical Analysis of Batting in Cricket,” Journal of Royal Statistical Society, 156, pp 443 –455, 1993.
[4] Damodaran, U, “Stochastic Dominance and Analysis of ODI Batting Performance: The Indian Cricket Team, 1989-2005,” Journal of Sports Science and Medicine, 5, pp 503 –508, 2006.
[5] Ovens M and Bukiet B. A mathematical modelling approachto one-day cricket batting orders.J Sports Sci Med5: 495–502.Preston I and Thomas J. Batting strategy in limited overscricket.Statistician49(1): 95–106, 2006
[6] Swartz TB, Gill PS, Beaudoin D and de Silva BM (2006). Opti-mal batting orders in one-day cricket.Comput Opns Res33:1939–1950, 2006
[7] Lemmer HH (2006). A measure of the current bowling performancein cricket.S Afr J Res Sport Phys Educ Recreation28(2): 91–103, 2006
[8] Lewis, A., “Extending the Range of Player-Performance Measures in One-Day Cricket,” Journal of Operational Research Society, 59, pp 729-742, 2008.
[9] Farhana Siddiqui, Hasan Phudinawala, Chetan Davale, Soham Pawar,” Innovative Idea for Playerelection usingSupport Vector Machine(SVM)” International Journal of Computer Sciences and Engineering, Vol. 7, Issue-4, pp.841-843, 2019
[10] C. Deep Prakash “A New Team Selection Methodology using Machine Learning and Memetic Genetic Algorithm for IPL-9”, International Journal ofElectronics, Electrical and Computational System Volume 5 –Issue.4, April 2016
[11] Sharp, Gary & Brettenny, Warren & Gonsalves, John & Lourens, Michelle & Stretch, R. Integer optimisation for the selection of a Twenty20 cricket team. Journal of the Operational Research Society. 62. 10.1057/jors.2010.122, 2011
[12] Ahmed, F., Deb, K., & Jindal, A. .Evolutionary multi-objective optimization and decision making approaches to cricket team selection.In Proceedings of the Second International Conference on Swarm, Evolutionary, and Memetic Computing. Berlin, Heidelberg: Springer-Verlaghttp://dx.doi.org/10.1007/978-3-642-27242-4_9, 2011
[13] K. Deb, S. Agrawal, A. Pratap, and T. Meyarivan. A fast and elitist multi-objective geneticalgorithm: NSGA-II.IEEE Transactions on Evolutionary Computation, 6(2):182–197, 2002.
[14] Nihar Patel, Mrudang Pandya,” IPL Player’s Performance Prediction” International Journal of Computer Sciences and Engineering, Vol. 7, Issue-5, pp.478-481, 2019
[15] Harsha Perera, Jack Davis & Tim B. Swartz Optimal lineups inTwenty20 cricket, Journal of Statistical Computation and Simulation,86:14,2888-2900,2016 DOI:10.1080/00949655.2015.1136629
[16] Taha HA (2003).Operations Research, An Introduction. 7th edn,Prentice Hall: Upper Saddle River, New Jersey
[17] Lakkaraju, P., and Sethi, S., “Correlating the Analysis of Opinionated Texts Using SAS®Text Analytics with Application of Sabermetrics to Cricket Statistics,” Proceedings of SASGlobal Forum 2012, 136, pp 1-10, 2012.