Dennis, Wisely Liu and Erwin, Alva and Galinium, Maulahikmah (2016) Data Mining Based User Profiling For Advertisement Serving. Bachelor thesis, Swiss German University.

Preview	Text Wisely Dennis 12112006 TOC.pdf Download (1MB) | Preview
	Text Wisely Dennis 12112006 1.pdf Restricted to Registered users only Download (691kB)
	Text Wisely Dennis 12112006 2.pdf Restricted to Registered users only Download (1MB)
	Text Wisely Dennis 12112006 3.pdf Restricted to Registered users only Download (937kB)
	Text Wisely Dennis 12112006 4.pdf Restricted to Registered users only Download (2MB)
	Text Wisely Dennis 12112006 5.pdf Restricted to Registered users only Download (352kB)
Preview	Text Wisely Dennis 12112006 Ref.pdf Download (541kB) | Preview

Abstract

Advertisement serving on website is a prosperous business with huge market and millions of dollar prospect. By placing right advertisement at right time and place to right people, advertiser can increase their revenue by huge margin. The question is how advertiser and broker can push the right advertisement to the right user. User profiling can be used to analyze user’s behavior and predict what kind of advertisement should be served to the website user. Data mining approach can be harnessed to help with user profiling process. With data mining technique, user’s trace can be used as data source for behavior analysis. This research is trying to do user profiling based on their browsing history stored on proxy server. Their browsing history will serve as the basis of content crawling for content analysis using Multinomial Naïve Bayes classifier. The result of profiling then will be used as the basis for serving advertisement to user. The result will be validated by asking user’s preferences and comparing it with profile generated by classifier engine. The result of the advertisement serving will be determined by user questionnaire method. The final result of this research is 70% accuracy of user profile generated by Multinomial Naïve Bayes. This accuracy value prove that user profile generated by using Multinomial Naïve Bayes can be used on advertisement serving.

Item Type:	Thesis (Bachelor)
Uncontrolled Keywords:	Advertisement Serving; Data Mining; Multinomial Naïve Bayes; Text Classification; Machine Learning
Subjects:	H Social Sciences > HF Commerce > HF5801 Advertising Q Science > QA Mathematics > QA76 Computer software > T Technology > T Technology (General) > T58.5 Information technology
Divisions:	Faculty of Engineering and Information Technology > Department of Information Technology
Depositing User:	Astuti Kusumaningrum
Date Deposited:	19 Oct 2020 14:55
Last Modified:	19 Oct 2020 14:55
URI:	http://repository.sgu.ac.id/id/eprint/922

Actions (login required)

View Item