GÜÇLENDIRME ALGORİTMALARI İLE TELEKOMÜNİKASYONDA MÜŞTERİ KAYBI TAHMİNİ

Yıl 2021, Cilt: 5 Sayı: Özel Sayı 1, 12 - 21, 01.03.2021

Ezgi Nazman

Öz

Customer churn is one of the major problems for large companies, especially in banking and telecommunication. Recently, telecommunication companies tend to prevent customer churn since the cost of gaining new customers is more than retaining existing customers. Therefore, the companies would like to have to determine potential churns using different prediction methods such as machine learning algorithms. XGBoost, Adaptive, and Gradient Boosting algorithms are widely used as supervised machine learning methods. Although boosting algorithms are known as superior algorithms in comparison with other machine learning methods, the performances of these models can be greatly affected when the data set is highly imbalanced. In the study, the data set including 26.4% churned customers were considered for the study to evaluate Boosting algorithms. Features are consist of the variables which can be related to the churn decision of the customers such as gender, online security, internet service, online backup, etc. Firstly, Exploratory data analysis was applied to understand the distribution of customers in terms of the related features. Then, the Adaptive-oversampling method was used to eliminate the imbalanced data problem. Lastly, in order to evaluate prediction results of the compared algorithms accuracy, precision, and F1 metrics were calculated for the prediction results. 10 fold cross-validation was also applied in order to validate accuracy results.

Anahtar Kelimeler

Customer Churn, Telecommunication, Machine Learning, Imbalanced Data

GÜÇLENDİRME ALGORİTMALARI İLE TELEKOMÜNİKASYONDA MÜŞTERİ KAYBI TAHMİNİ

Öz

Müşteri kaybı, özellikle bankacılık ve telekomünikasyon alanındaki büyük şirketler için en büyük sorunlardan biridir. Son zamanlarda, telekomünikasyon şirketleri, yeni müşteriler kazanmanın maliyeti, mevcut müşterileri elde tutmaktan daha fazla olduğu için müşteri kaybını önleme eğilimindedir. Bu nedenle şirketler, makine öğrenimi algoritmaları gibi farklı tahmin yöntemlerini kullanarak potansiyel kayıpları belirlemek istemektedir. XGBoost, Adaptive ve Gradyant Boost algoritmaları, denetimli makine öğrenimi yöntemleri olarak yaygın şekilde kullanılmaktadır. Güçlendirme algoritmaları, diğer makine öğrenimi yöntemlerine kıyasla üstün algoritmalar olarak bilinmesine rağmen, bu modellerin performansları, veri seti oldukça dengesiz olduğunda büyük ölçüde etkilenebilir. Çalışmada, güçlendirme algoritmalarını değerlendirmek için % 26,4'ü kaybedilen müşterileri içeren veri seti dikkate alınmıştır. Özellikler, müşterilerin cinsiyet, çevrimiçi güvenlik, internet hizmeti, çevrimiçi yedekleme gibi müşteri kaybetme durumuyla ilişkili olabilecek değişkenlerden oluşmaktadır. İlk olarak, Müşterilerin ilgili özellikler açısından dağılımını anlamak için keşifsel veri analizi uygulandı. Daha sonra, dengesiz veri problemini ortadan kaldırmak için Adaptive-oversampling yöntemi kullanılmıştır. Son olarak, karşılaştırılan algoritmaların tahmin sonuçlarını değerlendirmek amacıyla doğruluk, kesinlik ve F1 ölçümleri hesaplandı. Tahmin sonuçlarını doğrulamak için 10 kat çapraz geçerlilik de uygulandı.

Anahtar Kelimeler

Müşteri Kaybı, Telekomünikasyon, Makine Öğrenmesi, Dengesiz Veri

Kaynakça

• Ahmed, A. A., & Maheswari, D. (2017). “Churn Prediction on Huge Telecom Data Using Hybrid Firefly based classification”. Egyptian Informatics Journal, 18(3), 215–220.
• Amin, A., Al-Obeidat, F., Shah, B., Adnan, A., Loo, J., Anwar, S. (2019). “Customer Churn Prediction in Telecommunication Industry Using Data Certainty”. Journal of Business Research, 94, 290-301.
• Athanassopoulos, A. (2000). “Customer Satisfaction Cues to Support Market Segmentation and Explain Switching Behavior”. Journal of Business Research, 47(3), 191-207.
• Berson, A., Smith, S. & Thearling, K. (2000). Customer retention. In building data mining applications for CRM, New York:McGrawHill, Chapter 12.
• Ćamilović, D. (2008). “Data Mining and CRM in Telecommunications”. Serbian Journal of Management 3(1):61-72.
• Chen, T. & Guestrin, C. (2016). “XGBoost: A Scalable Tree Boosting System”. Cornell University, Computer Science, Machine Learning. arXiv:1603.02754.
• Coussement, K., Lessmann, S., and Verstraeten, G. (2017). “A Comparative Analysis of Data Preparation Algorithms for Customer Churn Prediction: A Case Study in the Telecommunication Industry”. Decision Support Systems. 95:27-36.
• Esteves, G., Mendes, M.J. (2016). “Churn prediction in the Telecom Business”, The Eleventh International Conference on Digital Information Management (ICDIM 2016), 254-259.
• He, H., Bai, Y., Garcia, E.A., and Li, S. (2008). “ADASYN: Adaptive Synthetic Sampling Approach for Imbalanced Learning”. International Joint Conference on Neural Networks (IJCNN 2008), IEEE.
• Farquad, M., Ravi, V., & Raju, S. B. (2014). “Churn Prediction Using Comprehensible Support Vector Machine: An Analytical CRM Application”. Applied Soft Computing, 19, 31–40.
• Freund, Y. & Schapire, R.E. (1997). “A Decision-theoretic Generalization of On-line Learning and an Application to Boosting”. Journal of Computer and System Sciences, 55(1):119–139.
• Friedman, J.H. (2002). “Stochastic Gradient Boosting”. Computational Statistics and Data Analysis. 38, 367–378.
• IBM Cognos Analytics 11.1.3. https://community.ibm.com/community/user/businessanalytics/ blogs/steven-macko/2019/07/11/telco-customer-churn-1113
• Idris, A., & Asifullah, K. (2014). “Ensemble based efficent churn prediction model for telecom”. 12th International Conference on Frontiers of Information Technology (FIT), 1–7.
• Kasiran, Z., Ibrahim, Z., Syahir, M., & Ribuan, M. (2014). “Customer Churn Prediction Using Recurrent Neural Network with Reinforcement Learning Algorithm in Mobile Phone Users”. International Journal of Intelligent Information Processing(IJIIP), 1–11.
• Kotler, P., Keller, K.L. (2009). Marketing Management. Pearson Prentice Hall.
• Maria, O., Verbeke, W., Sarraute, C., Baesens, B., & Vanthienen, J. (2016). “A Comparative Study of Social Network Classifiers for Predicting Churn in the Telecommunication Industry”. IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM),1151–1158.
• Mishra, A. And Reddy, U.S. (2017). “A Comparative Study of Customer Churn Prediction in Telecommunication Industry Using Ensemble Based Classifiers”. Proceedings of the International Conference on Inventive Computing and Informatics. IEEE Xplore Compliant - Part Number: CFP17L34-ART, ISBN: 978-1-5386-4031-9.
• Óskarsdóttir, M., Bravo, C., Verbeke, W., Sarraute, C., Baesens, B., & Vanthienen, J. (2017). “Social Network Analytics for Churn Prediction in Telco: Model Building, Evaluation, and Network Architecture”. Expert Systems with Applications, 85, 204–220.
• Rahman, S., Irfan, M., Raza, M., Ghori, K.M., Yaqoob, S., and Awais, M. (2020). “Performance Analysis of Boosting Classifiers in Recognizing Activities of Daily Living”. International Journal of Environmental Research and Public Health. 17, 1082, 1-15.
• Sharma, R. R., & Rajan, S. (2017). “Evaluating Prediction of Customer Churn Behavior Based on Artificial Bee Colony Algorithm”. International Journal of Engineering and Computer Science, 6(1), 20017–20021.
• Umayaparvathi, V. & Iyakutti, K. (2016). Customer churn prediction using big data analytics. Ph.D. Thesis from Blekinge Institute of Technology.
• Wei, C.P., and Chiu, I.T. (2002). “Turning Telecommunications Call Details to Churn Prediction: A Data Mining Approach”. Expert Systems with Applications 23:103-112.