Skip to main content

2016 | OriginalPaper | Buchkapitel

A Feature Extraction Method Based on Stacked Auto-Encoder for Telecom Churn Prediction

verfasst von : Ruiqi Li, Peng Wang, Zonghai Chen

Erschienen in: Theory, Methodology, Tools and Applications for Modeling and Simulation of Complex Systems

Verlag: Springer Nature Singapore

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Customer churn prediction is a key problem to customer relationship management systems of telecom operators. Efficient feature extraction method is crucial to telecom customer churn prediction. In this paper, stacked auto-encoder is introduced as a nonlinear feature extraction method, and a new hybrid feature extraction framework is proposed based on stacked auto-encoder and Fisher’s ratio analysis. The proposed method is evaluated on datasets provided by Orange, and experimental results verify that it is authentically able to enhance the performance of prediction models both on AUC and computing efficiency.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Tsai, C.F., Lu, Y.H.: Customer churn prediction by hybrid neural networks. J. Expert Syst. Appl. 36, 12547–12553 (2009)CrossRef Tsai, C.F., Lu, Y.H.: Customer churn prediction by hybrid neural networks. J. Expert Syst. Appl. 36, 12547–12553 (2009)CrossRef
2.
Zurück zum Zitat Qi, J., Zhang, L., Liu, Y., et al.: ADTreesLogit model for customer churn prediction. J. Ann. Oper. Res. 168, 247–265 (2009)MathSciNetCrossRefMATH Qi, J., Zhang, L., Liu, Y., et al.: ADTreesLogit model for customer churn prediction. J. Ann. Oper. Res. 168, 247–265 (2009)MathSciNetCrossRefMATH
3.
Zurück zum Zitat Kisioglu, P., Topcu, Y.I.: Applying bayesian belief network approach to customer churn analysis: a case study on the telecom industry of Turkey. J. Expert Syst. Appl. 38, 7151–7157 (2011)CrossRef Kisioglu, P., Topcu, Y.I.: Applying bayesian belief network approach to customer churn analysis: a case study on the telecom industry of Turkey. J. Expert Syst. Appl. 38, 7151–7157 (2011)CrossRef
4.
Zurück zum Zitat 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. J. Expert Syst. with Appl. 32, 277–288 (2007)CrossRef 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. J. Expert Syst. with Appl. 32, 277–288 (2007)CrossRef
5.
Zurück zum Zitat Glady, N., Baesens, B., Croux, C.: Modeling churn using customer lifetime value. J. Eur. J. Oper. Res. 197, 402–411 (2009)CrossRefMATH Glady, N., Baesens, B., Croux, C.: Modeling churn using customer lifetime value. J. Eur. J. Oper. Res. 197, 402–411 (2009)CrossRefMATH
6.
Zurück zum Zitat Van den Poel, D., Lariviere, B.: Customer attrition analysis for financial services using proportional hazard models. J. Eur. J. Oper. Res. 157, 196–217 (2004)CrossRefMATH Van den Poel, D., Lariviere, B.: Customer attrition analysis for financial services using proportional hazard models. J. Eur. J. Oper. Res. 157, 196–217 (2004)CrossRefMATH
7.
Zurück zum Zitat Yabas, U., Cankaya, H.C.: Churn prediction in subscriber management for mobile and wireless communications services. In: 2013 IEEE Globecom Workshops, pp. 991–995. IEEE Press, New York (2013) Yabas, U., Cankaya, H.C.: Churn prediction in subscriber management for mobile and wireless communications services. In: 2013 IEEE Globecom Workshops, pp. 991–995. IEEE Press, New York (2013)
8.
Zurück zum Zitat Al-Shboul, B., Faris, H., Ghatasheh, N.: Initializing genetic programming using fuzzy clustering and its application in churn prediction in the telecom industry. J. Malays. J. Comput. Sci. 28, 213–220 (2015)CrossRef Al-Shboul, B., Faris, H., Ghatasheh, N.: Initializing genetic programming using fuzzy clustering and its application in churn prediction in the telecom industry. J. Malays. J. Comput. Sci. 28, 213–220 (2015)CrossRef
9.
Zurück zum Zitat Wu, Y., Qi, J., Wang C.: The study on feature selection in customer churn prediction modeling. In: 2009 IEEE Systems, Man and Cybernetics, pp. 3205–3210. IEEE Press, New York (2009) Wu, Y., Qi, J., Wang C.: The study on feature selection in customer churn prediction modeling. In: 2009 IEEE Systems, Man and Cybernetics, pp. 3205–3210. IEEE Press, New York (2009)
10.
Zurück zum Zitat Lin, W.C., Tsai, C.F., Ke, S.W.: Dimensionality and data reduction in telecom churn prediction. J. Kybernetes 43, 737–749 (2014)CrossRef Lin, W.C., Tsai, C.F., Ke, S.W.: Dimensionality and data reduction in telecom churn prediction. J. Kybernetes 43, 737–749 (2014)CrossRef
11.
Zurück zum Zitat Wang, S., Li, D., Song, X., et al.: A feature selection method based on improved fisher’s discriminant ratio for text sentiment classification. J. Expert Syst. Appl. 38, 8696–8702 (2011)CrossRef Wang, S., Li, D., Song, X., et al.: A feature selection method based on improved fisher’s discriminant ratio for text sentiment classification. J. Expert Syst. Appl. 38, 8696–8702 (2011)CrossRef
12.
Zurück zum Zitat Zhang, M., Li, G., Gong, J., et al.: Predicting configuration performance of modular product family using principal component analysis and support vector machine. J. J. Cent. South Univ. 21, 2701–2711 (2014)CrossRef Zhang, M., Li, G., Gong, J., et al.: Predicting configuration performance of modular product family using principal component analysis and support vector machine. J. J. Cent. South Univ. 21, 2701–2711 (2014)CrossRef
13.
Zurück zum Zitat Van der MLJP PEO, van den HH J.: Dimensionality reduction: A comparative review. In: Tilburg, Netherlands: Tilburg Centre for Creative Computing, Tilburg University, Technical report. 2009-005(2009) Van der MLJP PEO, van den HH J.: Dimensionality reduction: A comparative review. In: Tilburg, Netherlands: Tilburg Centre for Creative Computing, Tilburg University, Technical report. 2009-005(2009)
14.
Zurück zum Zitat Goodfellow, I., Lee, H., Le, Q.V., et al.: Measuring invariances in deep networks. In: Advances in neural information processing systems, pp. 646–654 (2009) Goodfellow, I., Lee, H., Le, Q.V., et al.: Measuring invariances in deep networks. In: Advances in neural information processing systems, pp. 646–654 (2009)
15.
Zurück zum Zitat Fawcett, T.: An introduction to ROC analysis. J. Pattern Recogn. Lett. 27, 861–874 (2006)CrossRef Fawcett, T.: An introduction to ROC analysis. J. Pattern Recogn. Lett. 27, 861–874 (2006)CrossRef
Metadaten
Titel
A Feature Extraction Method Based on Stacked Auto-Encoder for Telecom Churn Prediction
verfasst von
Ruiqi Li
Peng Wang
Zonghai Chen
Copyright-Jahr
2016
Verlag
Springer Nature Singapore
DOI
https://doi.org/10.1007/978-981-10-2663-8_58