Gökçe Kalabalık, “Improving Classification Results Using Bagging and Boosting Ensemble Methods”, June 10, 2015 (Wednesday)

Computer Engineering Department Seminar #55:

	Title:	Improving Classification Results Using Bagging and Boosting Ensemble Methods
	Speaker:	Gökçe Kalabalık, M.Sc. candidate, Yasar University
	Date:	June 10, 2015 (Wednesday)
	Time:	14:45-15:30
	Venue:	Computer Networks Lab (New building, Level B2.)
	Language:	English

Abstract: Data mining applications are used to analyze mass databases for having meaningful output. Nowadays, customer churn prediction is one of the most common applications of data mining. The aim of customer churn prediction is identifying customers with high tendency to leave a company. Customer churn prediction classifies customers as churn and non-churn. In order to improve classification results bagging and boosting ensemble methods are used. In this seminar, these methods and their applications will be analyzed.