Our OOW10 session proposal – Case Study: Prepaid churn model with Oracle Data Mining

If you like the content just sign in with your free OTN account and a click on the vote button, your vote may make it possible to present, thanks :)


Subject: Case Study: Prepaid churn model with Oracle Data Mining

Abstract: This session is about a churn prediction study in Turkcell which is the leading GSM operator in Turkey. The session will start with an overview of the churn prediction problem and the existing data mining system in Turkcell so that the participants have some knowledge about the churn problem and the existing solution to this problem.

The session will also cover the advantages of in-database data mining and Oracle Data Mining. It will continue with the prepaid churn model which was created by using Oracle Data Mining. Then, the results and the performance that we get using Oracle Data Mining will be discussed.

About the presenter: Necdet Deniz Halıcıoğlu; I work for Turkcell Technology in Turkey. Since I began to work for Turkcell, Oracle Database and Oracle products became a part of my life. I have worked on ODS and Data Mining Projects. I also have an interest on churn prediction problem. I had several case studies about churn prediction. Data mining is getting more attractive for me every day and I like it more every day.


  1. yasinsaygili says:

    it is very important event for turkish oracle technologiest
    thanks to tonguc abi for your supports about this event

  2. See TurkCell’s Pre-paid Churn Model Prediction with Oracle Data Mining option on Exadata session at OOW10 21 Sep. 12:30 -13:30 at Moscone South – http://tinyurl.com/3a8y4c4

Leave a Reply to H.Tonguç Yılmaz Cancel reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s