Machine Learning Approach to Baseball Player Assessment using KNN, Logistic Regression, and Gaussian Naive Bayes

Authors: , ,

Abstract: This research employs a machine learning approach to assess and predict baseball player performance, utilizing three distinct algorithms: K Nearest Neighbors (KNN), Logistic Regression, and Gaussian Naive Bayes. The purpose of the study is to discover trends and insights for an end-to-end comprehension of player skills, which assists coaches, scouts, and team management to make well-informed decisions. Player dataset involves batting averages, overall game statistics and defensive approaches. Along with the data set applied in the study, the sports analytics process is also developed and the assessment of the baseball players being done. Moreover, this study leads to talent identification, strategy development in the game and planning. KNN is used to get player clusters, logistic regression used to make binary predictions and Gaussian Naïve Bayes approach used to get probability of occurrence.

Financial Engineering, E-ISSN: 2945-1140, Volume 3, 2025, Art. #2

PDF
XML
Cite
×
Citation Tools
WSEAS AMA
Osman Akanay Canbulat, Safiye Turgay, Esma Sedef Kara, "Machine Learning Approach to Baseball Player Assessment using KNN, Logistic Regression, and Gaussian Naive Bayes," WSEAS Transactions on Financial Engineering, vol. 3, pp. 14-21, 2025, DOI:
Osman Akanay Canbulat, Safiye Turgay, Esma Sedef Kara. Machine Learning Approach to Baseball Player Assessment using KNN, Logistic Regression, and Gaussian Naive Bayes. Financial Engineering. 2025;3:14-21.
Copy to Clipboard
Citation copied to Clipboard

Certification

---