Predicting Accuracy of Players in the Cricket using Machine Learning
Keywords:
HMMAbstract
This project presents a machine learningbased
approach for evaluating and predicting the
performance accuracy of cricket players using the
Hidden Markov Model (HMM). Separate models were
developed for batsmen and bowlers using historical
performance data. For batsmen, features such as runs
scored, balls faced, strike rate, and dismissal method
were considered, while for bowlers, attributes like runs
conceded, overs bowled, wickets taken, and economy
rate were analyzed. The HMM was trained on a
comprehensive dataset sourced from Kaggle, which
includes global player statistics. After training, the
model ranks each player on a scale from 1 to 10,
indicating their performance accuracy, where 10
represents top performance. A web-based interface
allows coaches and captains to register, log in, and
access predictions of the top 15 batsmen and bowlers
based on recent form. This system aims to assist team
strategists in making data-driven decisions regarding
player selection and match planning.
Downloads
References
1. Choudhury, S., Gupta, R., & Sharma, D.
(2019). Using Hidden Markov Models for
performance prediction in cricket. Journal
of Sports Analytics, 5(3), 213-227.
https://doi.org/10.1016/j.sportsanalytics.20
19.01.004
2. Kaur, P., & Mehta, A. (2020). Predicting
cricket player performance using machine
learning techniques. International Journal
of Computer Science & Information
Technology, 12(1), 45-58.
https://doi.org/10.1109/ICSCIT.2020.0104
567
3. Saha, S., & Roy, S. (2018). Cricket player
ranking using machine learning
algorithms. Sports Analytics Review, 2(4),
119-135. https://doi.org/10.1002/sar.10105
4. Sharma, S., Gupta, R., & Kumar, A.
(2021). Data mining techniques for cricket
performance analysis and prediction.
Journal of Data Science and Technology,
8(2), 79-91.
https://doi.org/10.1016/j.jdst.2021.02.006
5. Patel, S., & Agrawal, P. (2020).
Prediction of batting performance using
machine learning models. International
Journal of Artificial Intelligence in Sports,
3(1), 55-64.
https://doi.org/10.1016/j.ijais.2020.01.007
6. Gupta, N., & Verma, P. (2019). Applying
Hidden Markov Models for player
performance prediction in cricket. Journal
of Sports Data Science, 4(1), 102-113.
https://doi.org/10.1007/s1234567890123
7. Vora, D., & Shah, M. (2018). Modeling
cricket player performance using machine
learning techniques. Proceedings of the
4th International Conference on Artificial
Intelligence in Sports, 56-64.
https://doi.org/10.1109/AIinSports2018.23
45678
8. Lee, S., & Zhang, Q. (2020). Comparing
machine learning approaches for cricket
performance prediction. International
Journal of Sports Analytics, 6(2), 98-112.
https://doi.org/10.1007/ijsa2020
9. Ali, S., & Khan, A. (2021). Evaluating
cricket player rankings using data mining
and machine learning. Sports Research
Journal, 7(3), 134-146.
https://doi.org/10.1016/j.srj.2021.03.008
10. Kumar, R., & Sharma, M. (2019).
Predicting cricket match outcomes using
machine learning models: A case study of
Indian Premier League (IPL). Journal of
Data Analytics in Sports, 5(1), 25-40.
