Abstract Classifying multi-agent cooperative behavior is a fundamental problem in various scientific and engineering domains. In team sports, many cooperative plays can be manually labelled by experts. However, it requires high labour costs and a large amount of unlabelled data is not utilised. This paper examines semi-supervised learning methods for the classification of strategic cooperative plays (called screen plays) in basketball using a smaller labelled dataset and a larger unlabelled dataset. We compared the classification performance of two basic semi-supervised learning methods: self-training and label-propagation. Results show that the classification performance of the semi-supervised learning approaches improved upon the conventional supervised approach (SVM: support vector machine) for minor types of screen-plays (flare, pin, back, cross, and hand-off screen). For the feature importance, we found that self-training obtained similar or higher Sharpley values than SVM. Our approach has the potential to reduce manual labelling costs for detecting various cooperative behaviors.
{"title":"Cooperative play classification in team sports via semi-supervised learning","authors":"Z. Ziyi, K. Takeda, Keisuke Fujii","doi":"10.2478/ijcss-2022-0006","DOIUrl":"https://doi.org/10.2478/ijcss-2022-0006","url":null,"abstract":"Abstract Classifying multi-agent cooperative behavior is a fundamental problem in various scientific and engineering domains. In team sports, many cooperative plays can be manually labelled by experts. However, it requires high labour costs and a large amount of unlabelled data is not utilised. This paper examines semi-supervised learning methods for the classification of strategic cooperative plays (called screen plays) in basketball using a smaller labelled dataset and a larger unlabelled dataset. We compared the classification performance of two basic semi-supervised learning methods: self-training and label-propagation. Results show that the classification performance of the semi-supervised learning approaches improved upon the conventional supervised approach (SVM: support vector machine) for minor types of screen-plays (flare, pin, back, cross, and hand-off screen). For the feature importance, we found that self-training obtained similar or higher Sharpley values than SVM. Our approach has the potential to reduce manual labelling costs for detecting various cooperative behaviors.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":"21 1","pages":"111 - 121"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47787436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D. Bürger, Y. Ritter, S. Pastel, M. Sprich, T. Lück, M. Hacke, C. Stucke, K. Witte
Abstract Virtual reality (VR) is a tool used in sports to train specific situations under standardized conditions. However, it remains unclear whether improved performances from VR training can be transferred into real world (RW). Therefore, the current study compares beginner training of balance beam tasks in VR (simulated balance beam height, n = 17) with similar training in RW (n = 15). Both groups completed 12 training sessions (each 20 min) within six weeks in their respective environment. The training aimed to learn the one leg full turn on a balance beam with a height of 120 cm. Criteria were defined to analyze the movement quality before and after the intervention. Statistical analyses showed similar improvements in movement quality in RW for both training groups after the intervention (p < .05). These results indicate that the skills adapted in VR could be transferred into RW and that the VR training was as effective as the RW training in improving the movement quality of balance beam elements. Thereby, VR provides the advantages of a reduced risk of injury due to a simulated beam height, a faster beam height adjustment, and spacial independence from specific gyms.
{"title":"The Impact of Virtual Reality Training on Learning Gymnastic Elements on a Balance Beam with Simulated Height","authors":"D. Bürger, Y. Ritter, S. Pastel, M. Sprich, T. Lück, M. Hacke, C. Stucke, K. Witte","doi":"10.2478/ijcss-2022-0005","DOIUrl":"https://doi.org/10.2478/ijcss-2022-0005","url":null,"abstract":"Abstract Virtual reality (VR) is a tool used in sports to train specific situations under standardized conditions. However, it remains unclear whether improved performances from VR training can be transferred into real world (RW). Therefore, the current study compares beginner training of balance beam tasks in VR (simulated balance beam height, n = 17) with similar training in RW (n = 15). Both groups completed 12 training sessions (each 20 min) within six weeks in their respective environment. The training aimed to learn the one leg full turn on a balance beam with a height of 120 cm. Criteria were defined to analyze the movement quality before and after the intervention. Statistical analyses showed similar improvements in movement quality in RW for both training groups after the intervention (p < .05). These results indicate that the skills adapted in VR could be transferred into RW and that the VR training was as effective as the RW training in improving the movement quality of balance beam elements. Thereby, VR provides the advantages of a reduced risk of injury due to a simulated beam height, a faster beam height adjustment, and spacial independence from specific gyms.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":"21 1","pages":"93 - 110"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45890086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Cloud-based services revolutionize how applications are designed and provisioned in more and more application domains. Operating a cloud application, however, requires careful choices of configuration settings so that the quality of service is acceptable at all times, while cloud costs remain reasonable. We propose an analytical queuing model for cloud resource provisioning that provides an approximation on end-to-end application latency and on cloud resource usage, and we evaluate its performance. We pick an emerging use case of cloud deployment for validation: sports analytics. We have created a low-cost, cloud-based soccer player tracking system. We present the optimization of the cloud-deployed data processing of this system: we set the parameters with the aim of sacrificing as least as possible on accuracy, i.e., quality of service, while keeping latency and cloud costs low. We demonstrate that the analytical model we propose to estimate the end-to-end latency of a microservice-type cloud native application falls within a close range of what the measurements of the real implementation show. The model is therefore suitable for the planning of the cloud deployment costs for microservice-type applications as well.
{"title":"Optimizing and dimensioning a data intensive cloud application for soccer player tracking","authors":"Gergely Dobreff, Marton Molnar, László Toka","doi":"10.2478/ijcss-2022-0004","DOIUrl":"https://doi.org/10.2478/ijcss-2022-0004","url":null,"abstract":"Abstract Cloud-based services revolutionize how applications are designed and provisioned in more and more application domains. Operating a cloud application, however, requires careful choices of configuration settings so that the quality of service is acceptable at all times, while cloud costs remain reasonable. We propose an analytical queuing model for cloud resource provisioning that provides an approximation on end-to-end application latency and on cloud resource usage, and we evaluate its performance. We pick an emerging use case of cloud deployment for validation: sports analytics. We have created a low-cost, cloud-based soccer player tracking system. We present the optimization of the cloud-deployed data processing of this system: we set the parameters with the aim of sacrificing as least as possible on accuracy, i.e., quality of service, while keeping latency and cloud costs low. We demonstrate that the analytical model we propose to estimate the end-to-end latency of a microservice-type cloud native application falls within a close range of what the measurements of the real implementation show. The model is therefore suitable for the planning of the cloud deployment costs for microservice-type applications as well.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":"21 1","pages":"30 - 48"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46229918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jayamini Ranaweera, M. Zanin, D. Weaving, C. Withanage, G. Roe
Abstract Typical player management processes focus on managing an athlete’s physical, physiological, psychological, technical and tactical preparation and performance. Current literature illustrates limited attempts to optimize such processes in sports. Therefore, this study aimed to analyze the application of Business Process Management (BPM) in healthcare (a service industry resembling sports) and formulate a model to optimize data driven player management processes in professional sports. A systematic review, adhering to PRISMA framework was conducted on articles extracted from seven databases, focused on using BPM to digitally optimize patient related healthcare processes. Literature reviews by authors was the main mode of healthcare process identification for BPM interventions. Interviews with process owners followed by process modelling were common modes of process discovery. Stakeholder and value-based analysis highlighted potential optimization areas. In most articles, details on process redesign strategies were not explicitly provided. New digital system developments and implementation of Business Process Management Systems were common. Optimized processes were evaluated using usability assessments and pre-post statistical analysis of key process performance indicators. However, the scientific rigor of most experiments designed for such latter evaluations were suboptimal. From the findings, a stepwise approach to optimize data driven player management processes in professional sports has been proposed.
{"title":"Optimizing Player Management Processes in Sports: Translating Lessons from Healthcare Process Improvements to Sports","authors":"Jayamini Ranaweera, M. Zanin, D. Weaving, C. Withanage, G. Roe","doi":"10.2478/ijcss-2021-0008","DOIUrl":"https://doi.org/10.2478/ijcss-2021-0008","url":null,"abstract":"Abstract Typical player management processes focus on managing an athlete’s physical, physiological, psychological, technical and tactical preparation and performance. Current literature illustrates limited attempts to optimize such processes in sports. Therefore, this study aimed to analyze the application of Business Process Management (BPM) in healthcare (a service industry resembling sports) and formulate a model to optimize data driven player management processes in professional sports. A systematic review, adhering to PRISMA framework was conducted on articles extracted from seven databases, focused on using BPM to digitally optimize patient related healthcare processes. Literature reviews by authors was the main mode of healthcare process identification for BPM interventions. Interviews with process owners followed by process modelling were common modes of process discovery. Stakeholder and value-based analysis highlighted potential optimization areas. In most articles, details on process redesign strategies were not explicitly provided. New digital system developments and implementation of Business Process Management Systems were common. Optimized processes were evaluated using usability assessments and pre-post statistical analysis of key process performance indicators. However, the scientific rigor of most experiments designed for such latter evaluations were suboptimal. From the findings, a stepwise approach to optimize data driven player management processes in professional sports has been proposed.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":"20 1","pages":"119 - 146"},"PeriodicalIF":0.0,"publicationDate":"2021-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49358042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Mandorino, A. Figueiredo, Gianluca Cima, A. Tessitore
Abstract Predicting and avoiding an injury is a challenging task. By exploiting data mining techniques, this paper aims to identify existing relationships between modifiable and non-modifiable risk factors, with the final goal of predicting non-contact injuries. Twenty-three young soccer players were monitored during an entire season, with a total of fifty-seven non-contact injuries identified. Anthropometric data were collected, and the maturity offset was calculated for each player. To quantify internal training/match load and recovery status of the players, we daily employed the session-RPE method and the total quality recovery (TQR) scale. Cumulative workloads and the acute: chronic workload ratio (ACWR) were calculated. To explore the relationship between the various risk factors and the onset of non-contact injuries, we performed a classification tree analysis. The classification tree model exhibited an acceptable discrimination (AUC=0.76), after receiver operating characteristic curve (ROC) analysis. A low state of recovery, a rapid increase in the training load, cumulative workload, and maturity offset were recognized by the data mining algorithm as the most important injury risk factors.
{"title":"A Data Mining Approach to Predict Non-Contact Injuries in Young Soccer Players","authors":"M. Mandorino, A. Figueiredo, Gianluca Cima, A. Tessitore","doi":"10.2478/ijcss-2021-0009","DOIUrl":"https://doi.org/10.2478/ijcss-2021-0009","url":null,"abstract":"Abstract Predicting and avoiding an injury is a challenging task. By exploiting data mining techniques, this paper aims to identify existing relationships between modifiable and non-modifiable risk factors, with the final goal of predicting non-contact injuries. Twenty-three young soccer players were monitored during an entire season, with a total of fifty-seven non-contact injuries identified. Anthropometric data were collected, and the maturity offset was calculated for each player. To quantify internal training/match load and recovery status of the players, we daily employed the session-RPE method and the total quality recovery (TQR) scale. Cumulative workloads and the acute: chronic workload ratio (ACWR) were calculated. To explore the relationship between the various risk factors and the onset of non-contact injuries, we performed a classification tree analysis. The classification tree model exhibited an acceptable discrimination (AUC=0.76), after receiver operating characteristic curve (ROC) analysis. A low state of recovery, a rapid increase in the training load, cumulative workload, and maturity offset were recognized by the data mining algorithm as the most important injury risk factors.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":"20 1","pages":"147 - 163"},"PeriodicalIF":0.0,"publicationDate":"2021-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42296523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Quantification of athletic performance via analysis of scores of off-season fitness tests has become an essential part of the modern strength and conditioning coach (SCC). Player Efficiency Rating (PER) and Efficiency index (EFF) are two of the most used in-season basketball performance metrics in the US. We collected data from male and female basketball players of a National Collegiate Athletic Association (NCAA) program. Based on sex, we examined a) if unadjusted PER (uPER) and EFF reflect different amounts of information and b) which fitness tests predict those two indices more accurately. Our results showed lower means and less variability of the fitness tests scores in women than men. The correlation between uPER and EFF in men was moderate and strong in women. In men, no strong correlation was found between any fitness test and EFF, while full court sprint was strongly correlated with uPER. In women, strong correlations were detected between a) the T-drill and EFF and b) the foul court sprint, the vertical jump, and the T-drill and uPER. The collegiate SCCs should consider that off-season scores of a) the foul court drill may predict uPER more accurately in both men and women and b) the T-drill may predict both EFF and uPER more precisely in women.
{"title":"Offseason Fitness Tests a Collegiate Basketball Strength Coach Should Choose to Predict In-Season Perfomance Based on Sex","authors":"A. Stamatis, Z. Papadakis, G. Morgan, A. Boolani","doi":"10.2478/ijcss-2021-0010","DOIUrl":"https://doi.org/10.2478/ijcss-2021-0010","url":null,"abstract":"Abstract Quantification of athletic performance via analysis of scores of off-season fitness tests has become an essential part of the modern strength and conditioning coach (SCC). Player Efficiency Rating (PER) and Efficiency index (EFF) are two of the most used in-season basketball performance metrics in the US. We collected data from male and female basketball players of a National Collegiate Athletic Association (NCAA) program. Based on sex, we examined a) if unadjusted PER (uPER) and EFF reflect different amounts of information and b) which fitness tests predict those two indices more accurately. Our results showed lower means and less variability of the fitness tests scores in women than men. The correlation between uPER and EFF in men was moderate and strong in women. In men, no strong correlation was found between any fitness test and EFF, while full court sprint was strongly correlated with uPER. In women, strong correlations were detected between a) the T-drill and EFF and b) the foul court sprint, the vertical jump, and the T-drill and uPER. The collegiate SCCs should consider that off-season scores of a) the foul court drill may predict uPER more accurately in both men and women and b) the T-drill may predict both EFF and uPER more precisely in women.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":"20 1","pages":"164 - 174"},"PeriodicalIF":0.0,"publicationDate":"2021-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45998760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract To aid the implementation of athlete surveillance systems relative to logistical circumstances, easy-to-access information that summarises the extent to which methods of acquiring data are used in practice to monitor athletes is required. In this scoping review, Social Network Analysis and Mining (SNAM) techniques were used to summarise and identify the most prevalent combinations of methods used to monitor athletes in research studying team, individual, field- and court-based sports (357 articles; SPORTDiscus, MEDLINE, CINHAL, and WebOfScience; 2014-2018 inc.) . The most prevalent combination in team and field-based sports were HR and/or sRPE (internal) and GPS, whereas in individual and court-based sports, internal methods (e.g., HR and sRPE) were most prevalent. In court-based sports, where external methods were occasionally collected in combination with internal methods of acquiring data, the use of accelerometers or inertial measuring units (ACC/IMU) were most prevalent. Whilst individual and court-based sports are less researched, this SNAM-based summary reveals that court-based sports may lead the way in using ACC/IMU to monitor athletes. Questionnaires and self-reported methods of acquiring data are common in all categories of sport. This scoping review provides coaches, sport-scientists and researchers with a data-driven visual resource to aid the selection of methods of acquiring data from athletes in all categories of sport relative to logistical circumstances. A guide on how to practically implement a surveillance system based on the visual summaries provided herein, is also presented.
{"title":"A scoping review using social network analysis techniques to summarise the prevalance of methods used to acquire data for athlete survelliance in sport","authors":"P. J. Watson, J. Fieldsend, V. H. Stiles","doi":"10.2478/ijcss-2021-0011","DOIUrl":"https://doi.org/10.2478/ijcss-2021-0011","url":null,"abstract":"Abstract To aid the implementation of athlete surveillance systems relative to logistical circumstances, easy-to-access information that summarises the extent to which methods of acquiring data are used in practice to monitor athletes is required. In this scoping review, Social Network Analysis and Mining (SNAM) techniques were used to summarise and identify the most prevalent combinations of methods used to monitor athletes in research studying team, individual, field- and court-based sports (357 articles; SPORTDiscus, MEDLINE, CINHAL, and WebOfScience; 2014-2018 inc.) . The most prevalent combination in team and field-based sports were HR and/or sRPE (internal) and GPS, whereas in individual and court-based sports, internal methods (e.g., HR and sRPE) were most prevalent. In court-based sports, where external methods were occasionally collected in combination with internal methods of acquiring data, the use of accelerometers or inertial measuring units (ACC/IMU) were most prevalent. Whilst individual and court-based sports are less researched, this SNAM-based summary reveals that court-based sports may lead the way in using ACC/IMU to monitor athletes. Questionnaires and self-reported methods of acquiring data are common in all categories of sport. This scoping review provides coaches, sport-scientists and researchers with a data-driven visual resource to aid the selection of methods of acquiring data from athletes in all categories of sport relative to logistical circumstances. A guide on how to practically implement a surveillance system based on the visual summaries provided herein, is also presented.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":"20 1","pages":"175 - 197"},"PeriodicalIF":0.0,"publicationDate":"2021-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45276768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Many professional sport organizations are currently in the process of finding or already using sports information systems (SIS) to integrate data from different information and measurement systems. The problem is that requirements are very heterogeneous. That is why no consistent definition of SIS and their categories exist, and it is often not clear which fields and functions SIS must cover. This work aims to provide a structured comparison of commercial SIS available on the market to provide an overview of the relevant features and characterize categories. Following PRISMA guidelines, a systematic search for relevant SIS providers was conducted. A catalog of 164 review items was created to define relevant features of SIS and to conduct semi-standardized interviews with product representatives. Overall 36 eligible SIS from 11 countries were identified and 21 of them were interviewed. The analysis of the interviews has shown that there are features that are present in all SIS, whereas others differ or are generally less represented. As a result, different SIS categories have been defined. The study suggests a more differentiated categorization of SIS is necessary and terms need to be defined more precisely. This review should be considered when companies designing SIS or sport organizations select SIS.
{"title":"Sports Information Systems: A systematic review","authors":"Thomas Blobel, M. Rumo, M. Lames","doi":"10.2478/ijcss-2021-0001","DOIUrl":"https://doi.org/10.2478/ijcss-2021-0001","url":null,"abstract":"Abstract Many professional sport organizations are currently in the process of finding or already using sports information systems (SIS) to integrate data from different information and measurement systems. The problem is that requirements are very heterogeneous. That is why no consistent definition of SIS and their categories exist, and it is often not clear which fields and functions SIS must cover. This work aims to provide a structured comparison of commercial SIS available on the market to provide an overview of the relevant features and characterize categories. Following PRISMA guidelines, a systematic search for relevant SIS providers was conducted. A catalog of 164 review items was created to define relevant features of SIS and to conduct semi-standardized interviews with product representatives. Overall 36 eligible SIS from 11 countries were identified and 21 of them were interviewed. The analysis of the interviews has shown that there are features that are present in all SIS, whereas others differ or are generally less represented. As a result, different SIS categories have been defined. The study suggests a more differentiated categorization of SIS is necessary and terms need to be defined more precisely. This review should be considered when companies designing SIS or sport organizations select SIS.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":"20 1","pages":"1 - 22"},"PeriodicalIF":0.0,"publicationDate":"2021-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43207278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Correctly assessing the contributions of an individual player in a team sport is challenging. However, an ability to better evaluate each player can translate into improved team performance, through better recruitment or team selection decisions. Two main ideas have emerged for using data to evaluate players: Top-down ratings observe the performance of the team as a whole and then distribute credit for this performance onto the players involved. Bottom-up ratings assign a value to each action performed, and then evaluate a player based on the sum of values for actions performed by that player. This paper compares a variant of plus-minus ratings, which is a top-down rating, and a bottom-up rating based on valuing actions by estimating probabilities. The reliability of ratings is measured by whether similar ratings are produced when using different data sets, while the validity of ratings is evaluated through the quality of match outcome forecasts generated when the ratings are used as predictor variables. The results indicate that the plus-minus ratings perform better than the bottom-up ratings with respect to the reliability and validity measures chosen and that plus-minus ratings have certain advantages that may be difficult to replicate in bottom-up ratings.
{"title":"Comparing bottom-up and top-down ratings for individual soccer players","authors":"L. M. Hvattum, G. Gelade","doi":"10.2478/ijcss-2021-0002","DOIUrl":"https://doi.org/10.2478/ijcss-2021-0002","url":null,"abstract":"Abstract Correctly assessing the contributions of an individual player in a team sport is challenging. However, an ability to better evaluate each player can translate into improved team performance, through better recruitment or team selection decisions. Two main ideas have emerged for using data to evaluate players: Top-down ratings observe the performance of the team as a whole and then distribute credit for this performance onto the players involved. Bottom-up ratings assign a value to each action performed, and then evaluate a player based on the sum of values for actions performed by that player. This paper compares a variant of plus-minus ratings, which is a top-down rating, and a bottom-up rating based on valuing actions by estimating probabilities. The reliability of ratings is measured by whether similar ratings are produced when using different data sets, while the validity of ratings is evaluated through the quality of match outcome forecasts generated when the ratings are used as predictor variables. The results indicate that the plus-minus ratings perform better than the bottom-up ratings with respect to the reliability and validity measures chosen and that plus-minus ratings have certain advantages that may be difficult to replicate in bottom-up ratings.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":"20 1","pages":"23 - 42"},"PeriodicalIF":0.0,"publicationDate":"2021-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42319605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zureneth Govea, Francisco Pérez-Galarce, Alfredo Candia-Véjar
Abstract The Association of Tennis Professionals (ATP) distributes a considerable amount of money in prizes each year. Studies have shown that only the top 100 ranked players can self-finance; hence, it is convenient to introduce changes to the prize distribution to promote a more sustainable system. A Linear Programming model to distribute the tournament’s budget under a new concept for the fair distribution of prize money is proposed. Additionally, to distribute the prizes, a function based on the effort of the players is designed. The model was applied to tournaments to demonstrate the impact on improving the player’s prizes distribution.
{"title":"An optimization model for the fair distribution of prize money in ATP tournaments","authors":"Zureneth Govea, Francisco Pérez-Galarce, Alfredo Candia-Véjar","doi":"10.2478/ijcss-2022-0002","DOIUrl":"https://doi.org/10.2478/ijcss-2022-0002","url":null,"abstract":"Abstract The Association of Tennis Professionals (ATP) distributes a considerable amount of money in prizes each year. Studies have shown that only the top 100 ranked players can self-finance; hence, it is convenient to introduce changes to the prize distribution to promote a more sustainable system. A Linear Programming model to distribute the tournament’s budget under a new concept for the fair distribution of prize money is proposed. Additionally, to distribute the prizes, a function based on the effort of the players is designed. The model was applied to tournaments to demonstrate the impact on improving the player’s prizes distribution.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":"21 1","pages":"9 - 29"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44122031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：