Detection of Churned and Retained Users with Machine Learning Methods for Mobile Applications

  • Merve Gençer
  • Gökhan Bilgin
  • Özgür Zan
  • Tansel Voyvodaoğlu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8518)


This study aims to find the different behavior patterns of churned and retained mobile application users using machine learning approach. The data for this study is gathered from the users of a mobile application (iPhone & Android). As a machine learning classifier Support Vector Machines (SVM) are used for evaluating in the detection of churned and retained users. Several features are extracted from user data to discriminate different user behaviors. Successful results are obtained and user behaviors are classified with 93% and 98% accuracy. From the diversity perspective, results of this study can be used to evaluate the differences of churned and retained users in terms of diverse user groups.


Machine learning SVM mobile applications churned and retained users diversity applications classification mobile devices push notification user experience 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
  2. 2.
  3. 3.
  4. 4.
    Gençer, M., Bilgin, G., Zan, Ö., Voyvodaoğlu, T.: A New Framework for Increasing User Engagement in Mobile Applications Using Machine Learning Techniques. In: Marcus, A. (ed.) DUXU/HCII 2013, Part IV. LNCS, vol. 8015, pp. 651–659. Springer, Heidelberg (2013)Google Scholar
  5. 5.
    Van den Poel, D., Larivière, B.: Customer Attrition Analysis for Financial Services Using Proportional Hazard Models. European Journal of Operational Research 157(1), 196–217 (2004)CrossRefzbMATHGoogle Scholar
  6. 6.
    Au, T., Guangqin, M., Shaomin, L.: Applying And Evaluating Models To Predict Customer Attrition Using Data Mining Techniques. Journal of Comparative International Management 6(1) (2003)Google Scholar
  7. 7.
    Burez, J., Van den Poel, D.: CRM At A Pay-Tv Company: Using Analytical Models To Reduce Customer Attrition By Targeted Marketing For Subscription Services. Expert Systems with Applications 32(2), 277–288 (2007)CrossRefGoogle Scholar
  8. 8.
    Hung, S.-Y., Yen, D.C., Wang, H.-Y.: Applying data mining to telecom churn management. Expert Systems with Applications 31(3), 515–524 (2006)CrossRefGoogle Scholar
  9. 9.
    Coussement, K., Van den Poel, D.:Improving Customer Attrition Prediction By Integrating Emotions From Client/Company Interaction Emails And Evaluating Multiple Classifiers. Expert Systems with Applications, vol. 36(3(Pt. 2)), Pt. 2, pp. 6127-6134 (2009)Google Scholar
  10. 10.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer (2007)Google Scholar
  11. 11.
    Hu, X.: Data Mining Approach For Retailing Bank Customer Attrition Analysis. Applied Intelligence 22(1), 47–60 (2005)CrossRefGoogle Scholar
  12. 12.
    Wu, R.-C., Chen, R.-S., Chen, C.-C.C.J.Y.: Data Mining Application In Customer Relationship Management of Credit Card Business. In: IEEE Computer Software and Applications Conference, vol. 2 (2005)Google Scholar
  13. 13.
    Hoggart, C.J., Griffin, J.E.: A Bayesian Partition Model For Customer Attrition. In: Bayesian Methods with Applications to Science, Policy and Official Statistics (Selected Papers from The Sixth World Meeting of the International Society for Bayesian Analysis), pp. 223–232 (2001)Google Scholar
  14. 14.
    Schölkopf, B., Smola, A.: Learning with Kernels. MIT Press (2002)Google Scholar
  15. 15.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. John Wiley & Sons (2001)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Merve Gençer
    • 1
  • Gökhan Bilgin
    • 2
  • Özgür Zan
    • 1
  • Tansel Voyvodaoğlu
    • 1
  1. 1.Done Info. and Com. SystemsIstanbulTurkey
  2. 2.Dept. of Computer EngineeringYildiz Technical UniversityIstanbulTurkey

Personalised recommendations