Scholarlink

<p>The focus of this study is to analyze the careers of three prominent International Cricketers- Virat Kohli, Jos Buttler, and David Warner by leveraging statistical modelling and machine learning techniques. Metrics such as boundaries (fours and sixes) and averages were analyzed through Exploratory Data Analysis. Machine learning techniques such as Simple Linear Regression and Multiple Linear Regression were used to predicted future run totals and three classification algorithms (Logistic Regression, Support Vector Machines, and Naïve Bayes) predicted dismissal outcomes. Among the models tested, Support Vector Machines consistently achieved accuracies above 80%, Logistic Regression provided balanced performance across players, and Naïve Bayes demonstrated superior precision and recall (up to 94% precision and 92% recall). Beyond these results, the novelty of this work lies in its focus on individual player careers, the comparative framework applied across three international cricketers, and the way the dataset was cleaned and structured for career-level analysis. Comparative insights revealed Kohli’s stability under pressure, Buttler’s variability yet boundary-hitting strength, and Warner’s blend of aggression and consistency. By linking exploratory patterns with predictive modeling, the study not only forecasts performance but also provides practical insights that players, coaches, and analysts can use for more informed strategic decisions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Career analysis of cricketers in T20 internationals and prediction of runs

  • 期刊论文

  • 发表日期：

    2026年1月3日

查看全文
  • Atul. A. Das,
  • Muthu Thiruvengadam,
  • Benod Kumar Kondapavuluri,
  • G. R. Brindha

摘要

The focus of this study is to analyze the careers of three prominent International Cricketers- Virat Kohli, Jos Buttler, and David Warner by leveraging statistical modelling and machine learning techniques. Metrics such as boundaries (fours and sixes) and averages were analyzed through Exploratory Data Analysis. Machine learning techniques such as Simple Linear Regression and Multiple Linear Regression were used to predicted future run totals and three classification algorithms (Logistic Regression, Support Vector Machines, and Naïve Bayes) predicted dismissal outcomes. Among the models tested, Support Vector Machines consistently achieved accuracies above 80%, Logistic Regression provided balanced performance across players, and Naïve Bayes demonstrated superior precision and recall (up to 94% precision and 92% recall). Beyond these results, the novelty of this work lies in its focus on individual player careers, the comparative framework applied across three international cricketers, and the way the dataset was cleaned and structured for career-level analysis. Comparative insights revealed Kohli’s stability under pressure, Buttler’s variability yet boundary-hitting strength, and Warner’s blend of aggression and consistency. By linking exploratory patterns with predictive modeling, the study not only forecasts performance but also provides practical insights that players, coaches, and analysts can use for more informed strategic decisions.