PlayerRank: leveraging learning-to-rank AI for player positioning in cricket
Player prioritization is crucial in sports analysis, yet prioritizing based on playing position is underexplored. This paper focuses on using learning-to-rank machine learning models to select the best players for slots within a cricket team's batting order in Twenty20 International (T20I) matc...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2024
|
| Subjects: | |
| Online Access: | https://repository.londonmet.ac.uk/9811/58/PlayerRank_Leveraging_Learning-to-Rank_AI_for_Player_Positioning_in_Cricket.pdf https://repository.londonmet.ac.uk/9811/64/PlayerRank_Leveraging_Learning-to-Rank_AI_for_Player_Positioning_in_Cricket%20%281%29.pdf |
| _version_ | 1824446500756783104 |
|---|---|
| author | Hassan, Bilal Clough, Clare Siddiqi, Yusra Ali, Rao Faizan Arshed, Muhammad Asad |
| author_facet | Hassan, Bilal Clough, Clare Siddiqi, Yusra Ali, Rao Faizan Arshed, Muhammad Asad |
| author_sort | Hassan, Bilal |
| collection | LMU |
| description | Player prioritization is crucial in sports analysis, yet prioritizing based on playing position is underexplored. This paper focuses on using learning-to-rank machine learning models to select the best players for slots within a cricket team's batting order in Twenty20 International (T20I) matches. The aim is to build and train position-specific models to rank potential players for each position in the batting order. These models will use listwise ranking algorithms and an artificial neural network architecture to provide data-driven player rankings, enhancing impartiality and performance focus. Each position-specific model is trained to rank players based on their suitability for that position in the batting order, considering factors like performance metrics and specialization. The models are designed to increase impartiality and focus on player performance. The models achieve an average ordered pair accuracy of over 94%, demonstrating their effectiveness in ranking players for specific batting positions. The specialization of positions enhances the utility of the recommendations, providing a more informed approach to player selection. This study highlights the value of using machine learning models to prioritize players based on their suitability for specific batting positions in T20I matches. The models offer an im-partial and performance-focused approach, enhancing the overall quality of player selection in cricket teams. |
| first_indexed | 2025-02-19T01:16:09Z |
| format | Article |
| id | oai:repository.londonmet.ac.uk:9811 |
| institution | London Metropolitan University |
| language | English English |
| last_indexed | 2025-02-19T01:16:09Z |
| publishDate | 2024 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | eprints |
| spelling | oai:repository.londonmet.ac.uk:98112024-12-09T14:58:57Z https://repository.londonmet.ac.uk/9811/ PlayerRank: leveraging learning-to-rank AI for player positioning in cricket Hassan, Bilal Clough, Clare Siddiqi, Yusra Ali, Rao Faizan Arshed, Muhammad Asad 000 Computer science, information & general works 600 Technology 790 Recreational & performing arts Player prioritization is crucial in sports analysis, yet prioritizing based on playing position is underexplored. This paper focuses on using learning-to-rank machine learning models to select the best players for slots within a cricket team's batting order in Twenty20 International (T20I) matches. The aim is to build and train position-specific models to rank potential players for each position in the batting order. These models will use listwise ranking algorithms and an artificial neural network architecture to provide data-driven player rankings, enhancing impartiality and performance focus. Each position-specific model is trained to rank players based on their suitability for that position in the batting order, considering factors like performance metrics and specialization. The models are designed to increase impartiality and focus on player performance. The models achieve an average ordered pair accuracy of over 94%, demonstrating their effectiveness in ranking players for specific batting positions. The specialization of positions enhances the utility of the recommendations, providing a more informed approach to player selection. This study highlights the value of using machine learning models to prioritize players based on their suitability for specific batting positions in T20I matches. The models offer an im-partial and performance-focused approach, enhancing the overall quality of player selection in cricket teams. Institute of Electrical and Electronics Engineers (IEEE) 2024-12-05 Article PeerReviewed text en cc_by_nd_4 https://repository.londonmet.ac.uk/9811/58/PlayerRank_Leveraging_Learning-to-Rank_AI_for_Player_Positioning_in_Cricket.pdf text en cc_by_nd_4 https://repository.londonmet.ac.uk/9811/64/PlayerRank_Leveraging_Learning-to-Rank_AI_for_Player_Positioning_in_Cricket%20%281%29.pdf Hassan, Bilal, Clough, Clare, Siddiqi, Yusra, Ali, Rao Faizan and Arshed, Muhammad Asad (2024) PlayerRank: leveraging learning-to-rank AI for player positioning in cricket. IEEE Access, 12. pp. 177504-177519. ISSN 2169-3536 https://www.doi.org/10.1109/ACCESS.2024.3495528 10.1109/ACCESS.2024.3495528 10.1109/ACCESS.2024.3495528 |
| spellingShingle | 000 Computer science, information & general works 600 Technology 790 Recreational & performing arts Hassan, Bilal Clough, Clare Siddiqi, Yusra Ali, Rao Faizan Arshed, Muhammad Asad PlayerRank: leveraging learning-to-rank AI for player positioning in cricket |
| title | PlayerRank: leveraging learning-to-rank AI for player positioning in cricket |
| title_full | PlayerRank: leveraging learning-to-rank AI for player positioning in cricket |
| title_fullStr | PlayerRank: leveraging learning-to-rank AI for player positioning in cricket |
| title_full_unstemmed | PlayerRank: leveraging learning-to-rank AI for player positioning in cricket |
| title_short | PlayerRank: leveraging learning-to-rank AI for player positioning in cricket |
| title_sort | playerrank leveraging learning to rank ai for player positioning in cricket |
| topic | 000 Computer science, information & general works 600 Technology 790 Recreational & performing arts |
| url | https://repository.londonmet.ac.uk/9811/58/PlayerRank_Leveraging_Learning-to-Rank_AI_for_Player_Positioning_in_Cricket.pdf https://repository.londonmet.ac.uk/9811/64/PlayerRank_Leveraging_Learning-to-Rank_AI_for_Player_Positioning_in_Cricket%20%281%29.pdf |
| work_keys_str_mv | AT hassanbilal playerrankleveraginglearningtorankaiforplayerpositioningincricket AT cloughclare playerrankleveraginglearningtorankaiforplayerpositioningincricket AT siddiqiyusra playerrankleveraginglearningtorankaiforplayerpositioningincricket AT aliraofaizan playerrankleveraginglearningtorankaiforplayerpositioningincricket AT arshedmuhammadasad playerrankleveraginglearningtorankaiforplayerpositioningincricket |