Predicting the Performance of Bowlers in IPL: An Application of Artificial Neural Network

Saikia, Hemanta; Bhattacharjee, Dibyojyoti; Lemmer, Hermanus H.

doi:10.1080/24748668.2012.11868584

Cited by 27 publications

(15 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With that said, performance analysis research on cricket is now beginning to diversify, addressing a wider range of research questions and applications. For example, the time-motion characteristics of different playing positions have been a topic of study (Petersen et al, 2009), as well as the use of sophisticated mathematical techniques such as artificial neural networks for prediction of bowling performance (Saikia et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

Determinants of success in English domestic Twenty20 cricket

Najdan

Robins

Glazier

2014

International Journal of Performance Analysis in Sport

View full text Add to dashboard Cite

The purpose of this study was to investigate the determinants of success in Twenty20 cricket. 29 matches for winning teams and 30 matches for losing teams were analysed from the 2010 English domestic Twenty20 competition. Magnitude-based inferences, reported as effect sizes (ES), were used to characterise differences in performance indicators between winning and losing teams. The top 5 indicators of success were losing less wickets in the powerplay overs (ES = -1), losing less wickets between overs 7-10 (ES = -1), 50+ run partnerships (ES = 1), individual batsmen contributing 75+ runs (ES = 1) and 50-74 runs (ES = 1). In addition, winning teams scored a higher percentage of total runs to long-off (ES =0.4) and the off-side (ES = 0.2), and bowled a higher percentage of deliveries at a yorker (ES = 0.4) and short length (ES = 0.58) than losing teams. Collectively, these findings highlight that teams should retain wickets in the first 10 overs of an innings, without necessarily maximising the number of runs scored. In the final 10 overs, teams should outscore the opposition by hitting boundary 4s and avoid scoring a high percentage of runs from 1s. Moreover, from a bowling perspective, a more balanced strategy with regards to bowling length appears to be advantageous, as evidenced by the greater usage of short and yorker length deliveries by winning teams. Abstract The purpose of this study was to investigate the determinants of success in Twenty20 cricket. 29 matches for winning teams and 30 matches for losing teams were analysed from the 2010 English domestic Twenty20 competition. Magnitude-based inferences, reported as effect sizes (ES), were used to characterise differences in performance indicators between winning and losing teams. The top 5 indicators of success were losing less wickets in the powerplay overs (ES = -1), losing less wickets between overs 7-10 (ES = -1), 50+ run partnerships (ES = 1), individual batsmen contributing 75+ runs (ES = 1) and 50-74 runs (ES = 1). In addition, winning teams scored a higher percentage of total runs to long-off (ES =0.4) and the off-side (ES = 0.2), and bowled a higher percentage of deliveries at a yorker (ES = 0.4) and short length (ES = 0.58) than losing teams. Collectively, these findings highlight that teams should retain wickets in the first 10 overs of an innings, without necessarily maximising the number of runs scored. In the final 10 overs, teams should outscore the opposition by hitting boundary 4s and avoid scoring a high percentage of runs from 1s. Moreover, from a bowling perspective, a more balanced strategy with regards to bowling length appears to be advantageous, as evidenced by the greater usage of short and yorker length deliveries by winning teams.

show abstract

Section: Introductionmentioning

confidence: 99%

Determinants of success in English domestic Twenty20 cricket

Najdan

Robins

Glazier

2014

International Journal of Performance Analysis in Sport

View full text Add to dashboard Cite

show abstract

“…The artificial neural network's ability to correctly classify more than 75% of the players league status for fourteen different position comparisons is a key result. This surpasses the previous prediction rates reported using artificial neural networks in other team sports, such as those undertaken in cricket (Iyer and Sharda, 2009;Saikia, Bhattacharjee and Lemmer, 2012). Their studies could predict classification of batsmen and bowlers with accuracy levels ranging from 49% to 77%.…”

Section: Discussionmentioning

confidence: 60%

Identifying playing talent in professional football using artificial neural networks

Barron

Ball

Robins

et al. 2020

Journal of Sports Sciences

View full text Add to dashboard Cite

show abstract

“…These findings would appear logical as the players going on to play in the Premier League and a lower division in the following season should be the furthest apart in playing ability and the neural network performed best at identifying the category of the players in these two groups and the differences between them. The artificial neural network’s ability to correctly classify 78.8% of the player groupings for this model is an important result and it has outperformed other models that have been created to classify performance in cricket [ 18 , 19 ].…”

Section: Discussionmentioning

confidence: 99%

Artificial neural networks and player recruitment in professional soccer

2018

View full text Add to dashboard Cite

The aim was to objectively identify key performance indicators in professional soccer that influence outfield players’ league status using an artificial neural network. Mean technical performance data were collected from 966 outfield players’ (mean SD; age: 25 ± 4 yr, 1.81 ±) 90-minute performances in the English Football League. ProZone’s MatchViewer system and online databases were used to collect data on 347 indicators assessing the total number, accuracy and consistency of passes, tackles, possessions regained, clearances and shots. Players were assigned to one of three categories based on where they went on to complete most of their match time in the following season: group 0 (n = 209 players) went on to play in a lower soccer league, group 1 (n = 637 players) remained in the Football League Championship, and group 2 (n = 120 players) consisted of players who moved up to the English Premier League. The models created correctly predicted between 61.5% and 78.8% of the players’ league status. The model with the highest average test performance was for group 0 v 2 (U21 international caps, international caps, median tackles, percentage of first time passes unsuccessful upper quartile, maximum dribbles and possessions gained minimum) which correctly predicted 78.8% of the players’ league status with a test error of 8.3%. To date, there has not been a published example of an objective method of predicting career trajectory in soccer. This is a significant development as it highlights the potential for machine learning to be used in the scouting and recruitment process in a professional soccer environment.

show abstract

Predicting the Performance of Bowlers in IPL: An Application of Artificial Neural Network

Cited by 27 publications

References 9 publications

Determinants of success in English domestic Twenty20 cricket

Determinants of success in English domestic Twenty20 cricket

Identifying playing talent in professional football using artificial neural networks

Artificial neural networks and player recruitment in professional soccer

Contact Info

Product

Resources

About