TY - GEN
T1 - Predictive Analysis of Cricket Match Outcomes
T2 - 23rd International Conference on Hybrid Intelligent Systems, HIS 2023
AU - Suseela, G.
AU - Devi, B. Rupa
AU - Ashwitha, A.
AU - Venkataramana, R.
AU - Hussain, Shaik Jaffer
AU - Avanija, J.
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025
Y1 - 2025
N2 - Cricket, one of the most popular also widely followed sports globally, has garnered significant interest from enthusiasts and analysts. Predicting the outcome of cricket matches poses a challenging yet intriguing problem, with implications for sports enthusiasts, betting markets, and team strategies. This study delves into applying Machine Learning (ML) and Data Mining techniques to forecast cricket match results. By harnessing historical match data encompassing various facets of gameplay, including player statistics, weather conditions, venue characteristics, and toss outcomes, this research endeavors to build robust predictive models. Integrating ML algorithms, such as Decision Trees (DT), Support Vector Machines (SVM), Naive Bayes (NB), and Random Forest (RF), alongside sophisticated Data Mining methodologies promises to unlock hidden patterns and insights within the data. The aim is to develop accurate and reliable predictive models that can assist stakeholders in making informed decisions related to cricket match outcomes. In our research, the ML classifier’s accuracy is accordingly NB 91%, DT 90%, SVM 85%, and RF 89%. The highest AUC value achieved by the NB classifier was 93%. The NB classifier performs best in predicting the result of our research. The findings of this study provide valuable insights for coaches, analysts, and betting enthusiasts in the cricketing community.
AB - Cricket, one of the most popular also widely followed sports globally, has garnered significant interest from enthusiasts and analysts. Predicting the outcome of cricket matches poses a challenging yet intriguing problem, with implications for sports enthusiasts, betting markets, and team strategies. This study delves into applying Machine Learning (ML) and Data Mining techniques to forecast cricket match results. By harnessing historical match data encompassing various facets of gameplay, including player statistics, weather conditions, venue characteristics, and toss outcomes, this research endeavors to build robust predictive models. Integrating ML algorithms, such as Decision Trees (DT), Support Vector Machines (SVM), Naive Bayes (NB), and Random Forest (RF), alongside sophisticated Data Mining methodologies promises to unlock hidden patterns and insights within the data. The aim is to develop accurate and reliable predictive models that can assist stakeholders in making informed decisions related to cricket match outcomes. In our research, the ML classifier’s accuracy is accordingly NB 91%, DT 90%, SVM 85%, and RF 89%. The highest AUC value achieved by the NB classifier was 93%. The NB classifier performs best in predicting the result of our research. The findings of this study provide valuable insights for coaches, analysts, and betting enthusiasts in the cricketing community.
UR - https://www.scopus.com/pages/publications/105012919271
UR - https://www.scopus.com/pages/publications/105012919271#tab=citedBy
U2 - 10.1007/978-3-031-78925-0_42
DO - 10.1007/978-3-031-78925-0_42
M3 - Conference contribution
AN - SCOPUS:105012919271
SN - 9783031789243
T3 - Lecture Notes in Networks and Systems
SP - 425
EP - 432
BT - Hybrid Intelligent Systems - 23rd International Conference on Hybrid Intelligent Systems, HIS 2023
A2 - Bajaj, Anu
A2 - Madureira, Ana Maria
A2 - Abraham, Ajith
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 11 December 2023 through 13 December 2023
ER -