Design and Implementation of Statistical Estimation Based Model for Fair Assessment of Rain Interrupted Cricket Matches

  • Praveen D Chougale
Keywords: ODI cricket matches, Rain interrupted, Anova, Duck worth Lewis method, Neural network.


Cricket has achieved the status of a religion in India due to its huge popularity. The huge amounts of money and interest that cricket garners is increasing the spotlight on making the cricket experience for avid fans more seamless and enjoyable. There is a immediate requirement to come up with a fair assessment method which at any point of the game can decide the winner considering all relevant factors influencing the match. The current model used in rain interrupted matches is the Duckworth-Lewis (D/L) method. In interrupted matches a decision has to be reached within an allocated time of the game and the game cannot be postponed to another day. It has been reported that the D/L method delivers unrealistic target scores for certain cases exhibiting its unfairness and bias towards teams batting second. The proposed algorithm formulated is an alternate approach that could serve well to reset the target score overcoming this intrinsic problem of the D/L method. This algorithm demands extensive data cleaning and structuring of the raw available data, followed by feature extraction. Exploratory analysis and statistical tests have then been carried out on the independent variables. The developed mathematical functions work for both batting and bowling teams and the neural networks are trained to learn these functions. The developed algorithm is trained and validated for all the completed ODI matches as well as for D/L matches. Accuracy of the model tested on completed ODI matches and for rain interrupted matches is 57 % and 61% respectively. The implemented algorithm can be extended to player selection, modelling using other features (apart from batting and bowling related) to improve the prediction for the rain interrupted matchesimplementing a D/L method - for fairer evaluation of outcomes.


[1] Bailey, M. and Clarke, S. R. (2006) ‘Predicting the match outcome in one day international cricket matches, while the game is in progress’, in Journal of Sports Science andMedicine, pp. 480–487.
[2] Collins, M., Schapire, R. E. and Singer, Y. (2002) ‘Logistic regression, AdaBoost and Bregman distances’, Machine Learning, 48(1–3), pp. 253– 285. doi:
[3] Cricsheet(nodate).Available: ownloads/allmatches.
[4] Dangeti, P. (2017) Statistics for Machine Learning: Techniques for exploring supervised, unsupervised, and reinforcement learning models with Python and R,
[5] Emrouznejad, A. and Anouze, A. L. (2010) ‘Data envelopment analysis with classification and regression tree - A case of banking efficiency’, Expert Systems,
27(4), pp. 231–246. doi: 10.1111/j.1468-0394.2010.00516.x.
[6] Kampakis, S. and Thomas, W. (2015) ‘Using Machine Learning to Predict the Outcome of English County twenty over Cricket Matches’, in. doi: 10.1360/04yd0007.
[7] Kevin Markham (2014) ‘Simple guide to confusion matrix terminology’, Data School. Available at: confusionmatrix-terminology/.
[8] Lokhande, R. and Professor, A. (no date) ‘Live Cricket Score and Winning Prediction’, International Journal of Trend in Research and Development, 5(1), pp. 2394–9333. Available at:
[9] S., G., R., H.-W. and H.P., S. (2010) ‘A support vector machine for decision support in melanoma recognition’, Experimental Dermatology, 19(9), pp. 830–835. doi:
[10] Science, C. (2015) ‘Predicting a T20 cricket match result while the match is in progress Authors Name Fahad Munir ( 11201014 ) Md . Kamrul Hasan ( 11201032 ) Sakib Ahmed ( 11201009 ) Sultan Md . Quraish ( 11201017 ) Supervisor Rubel Biswas Moin Mostakim A thesis presented fo’, (11201014).
How to Cite
Chougale, P. D. (2020). Design and Implementation of Statistical Estimation Based Model for Fair Assessment of Rain Interrupted Cricket Matches. Asian Journal For Convergence In Technology (AJCT), 5(3), 72-77. Retrieved from