Genre e-sport gaming tournament classification using machine learning technique based on decision tree, Naïve Bayes, and random forest algorithm. Issue 1 (February 2021)

• Record Type: Journal Article
• Authors: Dikananda, Arif Rinaldi; Ali, Irfan; Fathurrohman, ; Ade Rinaldi, Rizki; Iin,
• Is Part Of: IOP conference series. Volume 1088:Issue 1(2021)
• Publication Date: 2021-02
• Subjects: Materials science -- Periodicals; 620.1105
• DOI: 10.1088/1757-899X/1088/1/012037
• Languages: English
• ISSNs: 1757-8981

Abstract

Abstract: The development of the game industry in this global era no longer presents entertaining games but also provides competitive games. With the recent competitive game, it can be categorized into a sport called e-Sport. Various game developers have also created e-Sport facilities and created a tournament to advance the industry. The increasing number of tournaments that are held in the field of sports from various types of games, it requires a classification for the types of games that are actively holding tournaments from the last few years. The classification used is Naive Bayes, decision tree and random forest algorithm. Naïve Bayes has become one of the algorithms for data. Naïve Bayes is a classification system based on the theorem of Bayes. Naïve Bayes is a classification system based on the theorem of Bayes. It's also recognized that the Naïve Bayes Classifier is greater than certain other classification methods. As first, the main aspect of Naïve Bayes is a very good (naive) presumption of freedom from any situation or case. It's also recognized that the Naïve Bayes Classifier is greater than certain other classification methods. As first, the main aspect of Naïve Bayes is a very good (naive) presumption of freedom from any situation or case. Decision trees are also well machine learning algorithms used to solve complex classification problems. Decision Tree is a classification method for data mining that aims to predict the behavior of the database. The result from this research is Random forest accuration 60%.