ISSN 0253-2778

CN 34-1054/N

open
Free to Publish. Free to Read.
Open AccessOpen Access JUSTC Original Paper

A two-stage feature selection method based on Fisher’s ratio and prediction risk for telecom customer churn prediction

  • Department of Automation, University of Science and Technology of China, Hefei, 230027, China

Funds:  Supported by the National Natural Science Foundation of China ( 61375079).
Cite this:
https://doi.org/10.3969/j.issn.0253-2778.2017.08.008
More Information
  • Author Bio:

    XU Ziwei, male, born in 1986, PhD candidate. Research field: Prediction control. E-mail: xziwei@mail.ustc.edu.cn

  • Corresponding author: CHEN Zonghai
  • Received Date: 18 March 2016
  • Rev Recd Date: 07 November 2016
  • Publish Date: 31 August 2017
    Abstract

  • Abstract

    Telecom customer churn prediction is crucial to the customer relationship management systems of telecom operators. It aims to predict a particular customer who is at a high risk of churning. The predicting process includes the steps of data pre-processing, imbalance processing, feature selection, classifier training and evaluation. A two-stage feature selection method based on fisher’s ratio and prediction risk was proposed, which took advantage of the filter feature selection method and wrapper feature selection method to solve the high dimensionality problem of telecom customer churn prediction. The method was evaluated on a real-world dataset, and the experimental results verify that it is able to reduce feature dimensionality and improve the performance of classifiers.

    Abstract

    Telecom customer churn prediction is crucial to the customer relationship management systems of telecom operators. It aims to predict a particular customer who is at a high risk of churning. The predicting process includes the steps of data pre-processing, imbalance processing, feature selection, classifier training and evaluation. A two-stage feature selection method based on fisher’s ratio and prediction risk was proposed, which took advantage of the filter feature selection method and wrapper feature selection method to solve the high dimensionality problem of telecom customer churn prediction. The method was evaluated on a real-world dataset, and the experimental results verify that it is able to reduce feature dimensionality and improve the performance of classifiers.
    • FullText(HTML)
  • loading
    • References(17)
  • [1]
    QIN H F. The application of data mining in telecommunication churn customer[J]. Research Journal of Applied Sciences, Engineering and Technology, 2012, 4(11): 1054-1057.
    [2]
    NICULESCU-MIZIL A, PERLICH C, SWIRSZCZ G, et al. Winning the KDD cup orange challenge with ensemble selection[C]// Proceedings of the International Conference on Knowledge Discovery in Data Competition. Paris : ACM Press, 2009: 23-24.
    [3]
    XIE J J, ROJKOVA V, PAL S, et al. A Combination of boosting and bagging for KDD cup 2009-fast scoring on a large database[C]// Proceedings of the International Conference on Knowledge Discovery in Data Competition. Paris : ACM Press, 2009: 35-43.
    [4]
    MILLER H, CLARKE S, LANE S, et al. Predicting customer behaviour: The University of Melbourne’s KDD cup report[C]// Proceedings of the International Conference on Knowledge Discovery in Data Competition. Paris : ACM Press, 2009: 45-55.
    [5]
    YABAS U, CANKAYA H C. Churn prediction in subscriber management for mobile and wireless communications services[C]// Proceeding of the IEEE GLOBECOM Workshops. Atlanta, USA : IEEE Press, 2013: 991-995.
    [6]
    IDRIS A, KHAN A. Ensemble based efficient churn prediction model for telecom[C]// Proceeding of 12th International Conference on Frontiers of Information Technology. Islamabad, Pakistan : ACM Press, 2014: 238-244.
    [7]
    IDRIS A, RIZWAN M, KHAN A. Churn prediction in telecom using random forest and PSO based data balancing in combination with various feature selection strategies[J]. Computers & Electrical Engineering, 2012, 38(6): 1808-1819.
    [8]
    PENG H C, LONG F H, DING C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8): 1226-1238.
    [9]
    XU Hong, ZHANG Zigang, ZHANG Yishi. Churn prediction in telecom using a hybrid two-phase feature selection method[C]// Proceeding of the Third IEEE International Symposium on Intelligent Information Technology Application. Nanchang, China: ACM Press, 2009: 576-579.
    [10]
    MANYIKA J, CHUI M, BROWN B, et al. Big data: The next frontier for innovation, competition, and productivity[R]. McKinsey Global Institute Report, New York, 2011.
    [11]
    WANG S G, LI D Y, WEI Y J, et al. A feature selection method based on fisher’s discriminant ratio for text sentiment classification[C]// Proceedings of the International Conference on Web Information Systems and Mining. Berlin: Springer, 2009: 88-97.
    [12]
    MOODY J. Prediction risk and architecture selection for neural networks[M]//From Statistics to Neural Networks. Berlin: Springer, 1994: 147-165.
    [13]
    ZAHARIA M, CHOWDHURY M, FRANKLIN M J, et al. Spark: Cluster computing with working sets[C]// Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing. Berkeley, USA: ACM Press, 2010: 10.
    [14]
    HUGEDOMAINS. 2009 knowledge discovery and data-mining competition[EB/OL]. http://www.kddcup-orange.com.
    [15]
    JAPKOWICZ N, STEPHEN S. The class imbalance problem: A systematic study[J]. Intelligent Data Analysis, 2002, 6(5): 429-449.
    [16]
    BREIMAN L. Manual on setting up, using, and understanding random forests v3. 1. 2002[EB/OL]. http://oz.berkeley.edu/users/breiman/Using_random_forests_V3.1.pdf[2015-12-30] .
    [17]
    DAVIS J, GOADRICH M. The relationship between precision-recall and ROC curves[C]// Proceedings of the 23rd International Conference on Machine Learning. Pittsburgh, USA: ACM Press, 2006: 233-240.
    • Supplements(0)
    • Related Articles
    • Track Citations
  • 加载中

Catalog

    |
    Get Citation
    PDF
    XML
    [1]
    QIN H F. The application of data mining in telecommunication churn customer[J]. Research Journal of Applied Sciences, Engineering and Technology, 2012, 4(11): 1054-1057.
    [2]
    NICULESCU-MIZIL A, PERLICH C, SWIRSZCZ G, et al. Winning the KDD cup orange challenge with ensemble selection[C]// Proceedings of the International Conference on Knowledge Discovery in Data Competition. Paris : ACM Press, 2009: 23-24.
    [3]
    XIE J J, ROJKOVA V, PAL S, et al. A Combination of boosting and bagging for KDD cup 2009-fast scoring on a large database[C]// Proceedings of the International Conference on Knowledge Discovery in Data Competition. Paris : ACM Press, 2009: 35-43.
    [4]
    MILLER H, CLARKE S, LANE S, et al. Predicting customer behaviour: The University of Melbourne’s KDD cup report[C]// Proceedings of the International Conference on Knowledge Discovery in Data Competition. Paris : ACM Press, 2009: 45-55.
    [5]
    YABAS U, CANKAYA H C. Churn prediction in subscriber management for mobile and wireless communications services[C]// Proceeding of the IEEE GLOBECOM Workshops. Atlanta, USA : IEEE Press, 2013: 991-995.
    [6]
    IDRIS A, KHAN A. Ensemble based efficient churn prediction model for telecom[C]// Proceeding of 12th International Conference on Frontiers of Information Technology. Islamabad, Pakistan : ACM Press, 2014: 238-244.
    [7]
    IDRIS A, RIZWAN M, KHAN A. Churn prediction in telecom using random forest and PSO based data balancing in combination with various feature selection strategies[J]. Computers & Electrical Engineering, 2012, 38(6): 1808-1819.
    [8]
    PENG H C, LONG F H, DING C. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8): 1226-1238.
    [9]
    XU Hong, ZHANG Zigang, ZHANG Yishi. Churn prediction in telecom using a hybrid two-phase feature selection method[C]// Proceeding of the Third IEEE International Symposium on Intelligent Information Technology Application. Nanchang, China: ACM Press, 2009: 576-579.
    [10]
    MANYIKA J, CHUI M, BROWN B, et al. Big data: The next frontier for innovation, competition, and productivity[R]. McKinsey Global Institute Report, New York, 2011.
    [11]
    WANG S G, LI D Y, WEI Y J, et al. A feature selection method based on fisher’s discriminant ratio for text sentiment classification[C]// Proceedings of the International Conference on Web Information Systems and Mining. Berlin: Springer, 2009: 88-97.
    [12]
    MOODY J. Prediction risk and architecture selection for neural networks[M]//From Statistics to Neural Networks. Berlin: Springer, 1994: 147-165.
    [13]
    ZAHARIA M, CHOWDHURY M, FRANKLIN M J, et al. Spark: Cluster computing with working sets[C]// Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing. Berkeley, USA: ACM Press, 2010: 10.
    [14]
    HUGEDOMAINS. 2009 knowledge discovery and data-mining competition[EB/OL]. http://www.kddcup-orange.com.
    [15]
    JAPKOWICZ N, STEPHEN S. The class imbalance problem: A systematic study[J]. Intelligent Data Analysis, 2002, 6(5): 429-449.
    [16]
    BREIMAN L. Manual on setting up, using, and understanding random forests v3. 1. 2002[EB/OL]. http://oz.berkeley.edu/users/breiman/Using_random_forests_V3.1.pdf[2015-12-30] .
    [17]
    DAVIS J, GOADRICH M. The relationship between precision-recall and ROC curves[C]// Proceedings of the 23rd International Conference on Machine Learning. Pittsburgh, USA: ACM Press, 2006: 233-240.
    Recommended articles
    TrendMD
    Volume 47 Issue 8 page: 686-694
    Cover

    Article Metrics

    Article views (399) PDF downloads(165)
    Proportional views

    Copyright © Editorial Office of JUSTC, All Rights Reserved. 皖ICP备05002528号

    Supported by: Beijing Renhe Information Technology Co. Ltd    

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return