MACHINE LEARNING-BASED TEST CRICKET PLAYER PERFORMANCE PREDICTION USING RANDOM FOREST, KNN AND NAÏVE BAYES

Algubelli Sankara Rao; Dr. A. Mary Sowjanya; Varsha Kumari

doi:10.5281/zenodo.22293333

Abstract

In today's era of sports analytics, historical performance data plays a crucial role in selecting players, preparing for
matches, and creating fantasy teams in Test cricket, making predictions more significant. This project proposes a
framework of machine learning based automatic prediction of Test cricket player performance with structured career
statistics. The system takes in the batting, bowling, and all-round statistics of a player from three different sets of
data (Batsmen, Bowlers, All-rounders). Data is preprocessed using numerical value cleaning, handling of missing
values, feature selection and normalization of data before it is analysed with classifiers such as Random Forest (RF),
K-Nearest Neighbors (KNN) and Naïve Bayes (NB). The trained models are able to categorize the players as Above
Average and Below Average performers, as well as producing confidence scores for each prediction. The
experimental results show that the Random Forest algorithm performs the best in predicting the outcomes and can
be applicable in real-world cricket analytics applications. The trained models are then integrated into a web
application using Flask to give a user a possibly interactive interface to upload CSV files, compare prediction models,
search player records, download prediction reports and get fantasy player recommendations. The proposed system
provides a scalable, accessible, and efficient system that helps coaches, analysts, selectors, and fantasy cricket
enthusiasts with data-driven decision making, showcasing the potential of utilizing machine learning in the realm of
Test cricket performance.

Keywords

Test Cricket, Machine Learning, Random Forest, K-Nearest Neighbors, Naïve Bayes, Flask, Player Performance Prediction.

References

1) Sumathi, M., Prabu, S. and Rajkamal, M., “Cricket Players Performance Prediction and Evaluation Using
Machine Learning Algorithms”, 2023 IEEE International Conference on Networking and Communications
(ICNWC), 2023, pp. 1–6, doi: 10.1109/ICNWC57852.2023.10127503.
2) Y. P. Kumar, J. S. Prakash, N. P. S., and S. Ramadass, “Utilizing Machine Learning for Sport Data Analytics
in Cricket: Score Prediction and Player Categorization”, 2023 IEEE 3rd Mysore Sub Section International
Conference (MysuruCon), 2023, doi: 10.1109/MysuruCon59703.2023.10396955
3) R. A. Mehtab, M. Mehtab, and A. Aburas, “ICC World Cup Prediction Based on Data Analytics and Business
Intelligence Techniques,” in 2018 International Conference on Cyber-Enabled Distributed Computing and
Knowledge Discovery (CyberC), 2018, pp. 273–279, doi: 10.1109/CyberC.2018.00056.
4) H. Inam-Ul-Haq, I. Ul Hassan and H. A. Shah, “Machine Learning Techniques for Result Prediction of One
Day International (ODI) Cricket Match,” 2023 IEEE 8th International Conference for Convergence in
Technology (I2CT), 2023, doi: 10.1109/I2CT57861.2023.10126241.
5) B. Hassan, C. Clough, Y. Siddiqi, R. F. Ali and M. A. Arshed, “PlayerRank: Leveraging Learning-to-Rank
AI for Player Positioning in Cricket,” IEEE Access, vol. 12, pp. 177504–177519, 2024, doi:
10.1109/ACCESS.2024.3495528.
6) K. Kumar, A. K. S., and V. Lakshmi, “Live Cricket Predictions for Runs and Win using Machine Learning,”
in 2024 IEEE 12th International Conference on Intelligent Systems (IS), 2024, doi:
10.1109/IS61756.2024.10705216.
7) S. Sanjaykumar, K. Udaichi, G. Rajendiran, M. Cretu, and Z. Kozina, “Cricket Performance Predictions: A
Comparative Analysis of Machine Learning Models for Predicting Cricket Player's Performance,” 2024 MIT
Art, Design and Technology School of Computing International Conference (MITADTSoCiCon), IEEE,
2024.
8) Swamynathan, Rajendiran, C. Udaichi, M. Cretu and Z. Kozina, “Cricket Performance Predictions: A
Comparative Analysis of Machine Learning Models for Prediction of Cricket Player’s Performance during
ODI World Cup 2023,” IEEE, 2024, 2024 MITADTSoCiCon
9) S. K. Harish, V. Kumar, and S. Ramesh, “Cricket Player Prediction of Role in a Team Using ML
Techniques,” in 2024 International Conference on E-Mobility, Power Control and Smart Systems (ICEMPS),
IEEE, 2024.
10) S. K. Harish, V. Kumar and S. Ramesh, “Algorithms for Performance Prediction in Cricket – Factors
Influencing the Player”, IEEE Conference Proceedings, 2024, doi: 10.1109/10847437.