Telekomünikasyon Sektöründe Müşteri Kaybının Makine Öğrenmesi Yöntemleriyle Analizi

Yıl 2023, , 2185 - 2208, 24.10.2023

Özge Nalan Bilişik , Damla Tuğba Sarp

https://doi.org/10.29130/dubited.1061257

Cited By: 1

Öz

Günümüz koşullarında şirketler arasındaki rekabet koşullarının artması, pazarlama stratejilerinin gelişmesi ve şirketlerin değişimi ve gelişimi ile müşteri ve müşteri sadakati önem kazanmıştır. Bir şirketin ayakta kalabilmesi için müşteri kazanmak önemlidir. Telekom sektöründe mevcut bir müşteriyi elde tutmak, yeni bir müşteri kazanmaktan daha az maliyetlidir. Müşteri kaybı analizi teklif ve davranışların incelenerek şirketi bırakma isteği yüksek olan müşterilerin tahmin edilmesi sürecidir. Müşteri kaybı analizi, başka bir şirkete geçmeyi planlayan müşterileri tahmin ederek, şirket bağlılığını artırmaya yönelik çeşitli kampanyalar geliştirmeye yönelik hizmetler sunmaktadır. Bu sayede firmaya rekabet avantajı sağlamaktadır. Bu çalışmanın amacı, telekomünikasyon sektöründe veri madenciliği ve makine öğrenmesi yöntemleriyle müşteri kayıplarını modelleyerek tahminlerde bulunmaktır. Ayrıca bu makaledeki uygulamanın gelecekte telekomünikasyon ve diğer sektörlerde farklı veri setleri ile müşteri kayıplarını analiz etmek isteyecek veri analistlerine ve akademisyenlere katkı sağlayacağı düşünülmektedir. Bu çalışmadaki analiz, açık erişimli bir veri tabanından elde edilen, 7043 müşteriye ait 20 işlem kaydını ve müşterilerin şirketten ayrılıp ayrılmadığını içeren bir veri seti üzerinde gerçekleştirilmiştir. Veri madenciliği yöntemlerinden Rastgele Orman (RF), Destek Vektör Makineleri (SVM) ve Çok Katmanlı Yapay Sinir Ağları (YSA) açık kaynaklı Phyton Ortamında modellenmiştir. Sonuçlar analiz edildiğinde, YSA müşterileri sınıflandırmada diğer makine öğrenimi yöntemlerinden daha başarılı olmuştur.

Anahtar Kelimeler

Müşteri Kaybı, Makine Öğrenmesi, YSA, DVM, RO

Analysis of Customer Churn in Telecommunication Industry with Machine Learning Methods

Öz

In today's conditions, customer loyalty has gained importance with the increase in the competitive environment between companies, the development of marketing strategies and the improvement of companies. Therefore, it is essential to acquire customers for a company to survive. Retaining an existing customer in the telecommunication sector is less costly than gaining a new customer. Customer churn analysis is the process of predicting customers with high abandonment requests by examining the offers and utilizable behaviors. Customer churn analysis provides services to develop various campaigns aiming to increase the company’s loyalty by predicting the customers who are planning to move to another company. In this way, it gives the company a competitive advantage. This study aims to make predictions by developing models for customer churns through data mining and machine learning methods in the telecommunication sector. In addition, we believe that the application in this article will contribute to data analysts and academicians who will want to analyze customer churn with different data sets in telecommunication and other sectors in the future. The analysis in this study is carried out on a data set obtained from an open-access database, including 20 transaction records for the customer from 7043 customers and whether the customer left the company. Among the data mining methods, Random Forest (RF), Support Vector Machines (SVM) and Multilayer Artificial Neural Networks (ANN) are modeled in open-source Phyton environment. The results have shown that ANN has fared better at classifying customers than other machine learning methods.

Anahtar Kelimeler

Customer Churn, Machine Learning, ANN, SVM, RF

Kaynakça

• [1] K. K. Tsiptsis and A. Chorianopoulos, Data mining techniques in CRM: inside customer segmentation. John Wiley & Sons, 2011.
• [2] F. Bagheri and M. J. Tarokh, “Customer Behavior mining based on RFM model to improve the customer relationship management,” J. Ind. Eng. Manag., vol.1, no. 1, 2014.
• [3] M. A. H. Farquad, V. Ravi, and S. B. Raju, “Churn prediction using comprehensible support vector machine: An analytical CRM application,” Appl. Soft Comput., vol. 19, pp. 31–40, 2014.
• [4] B. Heinrich and M. Helfert, “Analyzing Data Quality Investments in CRM-A model-based approach,” 8th International Conference on Informations Quality (ICIQ), Massachusetts Institute of Technology, pp. 80-95, 2003.
• [5] S. E. Seker, “Müşteri Kayıp Analizi (Customer Churn Analysis),” YBS Ansiklopedi, vol. 3, no. 1, pp. 26–29, 2016.
• [6] S.-Y. Hung, D. C. Yen, and H.-Y. Wang, “Applying data mining to telecom churn management,” Expert Syst. Appl., vol. 31, no. 3, pp. 515–524, 2006.
• [7] J. Hadden, A. Tiwari, R. Roy, and D. Ruta, “Computer assisted customer churn management: State-of-the-art and future trends,” Comput. Oper. Res., vol. 34, no. 10, pp. 2902–2917, 2007.
• [8] A. K. Ahmad, A. Jafar, and K. Aljoumaa, “Customer churn prediction in telecom using machine learning in big data platform,” J. Big Data, vol. 6, no. 1, pp. 1–24, 2019.
• [9] P. Lalwani, M. K. Mishra, J. S. Chadha, and P. Sethi, “Customer churn prediction system: a machine learning approach,” Computing, vol. 104, no. 2, pp. 271–294, 2022.
• [10] D. Das Adhikary and D. Gupta, “Applying over 100 classifiers for churn prediction in telecom companies,” Multimed. Tools Appl., vol. 80, no. 28, pp. 35123–35144, 2021.
• [11] N. Alboukaey, A. Joukhadar, and N. Ghneim, “Dynamic behavior based churn prediction in mobile telecom,” Expert Syst. Appl., vol. 162, p. 113779, 2020.
• [12] P. Swetha and B. Dayananda, “Improvised_XgBoost machine learning algorithm for customer churn prediction,” EAI Endorsed Trans. Energy Web, vol. 7, no. 30, p. e14, 2020.
• [13] B. Mishachandar and K. A. Kumar, “Predicting customer churn using targeted proactive retention,” Int. J. Eng. Technol., vol. 7, no. 2.27, p. 69, 2018.
• [14] I. Ullah, B. Raza, A. K. Malik, M. Imran, S. U. Islam, and S. W. Kim, “A churn prediction model using random forest: analysis of machine learning techniques for churn prediction and factor identification in telecommunication sector,” IEEE access, vol. 7, pp. 60134–60149, 2019.
• [15] B. Rani and S. Kant, “Semi-supervised learning approach to improve machine learning algorithms for churn analysis in telecommunication.”, Int. J. Comput. Inf. Syst. Ind. Manag. Appl. ISSN 2150-7988, vol. 12, 2020, pp. 265-275
• [16] N. Almufadi, A. M. Qamar, R. U. Khan, and M. T. Ben Othman, “Deep learning-based churn prediction of telecom subscribers.” Int. J. Eng. Res., ISSN 0974-3154, vol. 12, no. 12, pp. 2743-2748, 2019.
• [17] C. R. Jyothi, N. B. Boyina, S.V. Lakshmi, B. Akhila, & A. R. Sai, “A churn detection model in telecommunication using machine learning techniques,” J. Adv. Res. Dyn. Control Syst., vol 12, no. 2, pp. 936-943, 2020.
• [18] J. Pamina, B. Raja, S. SathyaBama, M. S. Sruthi, and A. VJ, “An effective classifier for predicting churn in telecommunication,” J. Adv. Res. Dyn. Control Syst., vol. 11, 2019(a).
• [19] W. N. Wassouf, R. Alkhatib, K. Salloum, and S. Balloul, “Predictive analytics using big data for increased customer loyalty: Syriatel Telecom Company case study,” J. Big Data, vol. 7, no. 1, pp. 1–24, 2020.
• [20] A. M. N. Alzubaidi and E. S. Al-Shamery, “Projection pursuit Random Forest using discriminant feature analysis model for churners prediction in telecom industry.,” Int. J. Electr. Comput. Eng., vol. 10, no. 2, 2020.
• [21] K. N. Rao, G. V. Nath, K. Tanmaya, B. Roja, B. Pravallika, and S. N. Aslam, “Business KPIs analysis using visual basics,” Int. J. Eng. Innov. Technol., vol. 8, no. 6S, 2020.
• [22] M. Malleswari, R. Maniraj, and P. Kumar, “Murugan: Comparative analysis of machine learning techniques to identify churn for telecom data,” Int. J. Eng. Technol, vol. 7, no. 3.34, pp. 291–295, 2018.
• [23] R. Suguna, S. Devi, and R. Mathew, “Customer churn predictive analysis by component minimization using machine learning,” Int. J. Innov. Technol. Explor. Eng., vol. 8, no. 8, pp. 3229–3233, 2019.
• [24] A. Isabella Amali, R. Arunkumar, and S. Mohan, “Comparing and evaluating machine learning algorithms for predicting customer churn in telecommunication industry,” J. Adv. Res. Dyn. Control Syst., vol. 11, no. 6 Special Issue, 2019, pp. 170-178.
• [25] J. B. Raja and S. C. Pandian, “An optimal ensemble classification for predicting churn in telecommunication.,” J. Eng. Sci. Technol. Rev., vol. 13, no. 2, 2020.
• [26] S. M. Jaisakthi, N. Gayathri, K. Uma, and V. Vijayarajan, “Customer Churn prediction using stochastic gradient boosting technique,” J. Comput. Theor. Nanosci., vol. 15, no. 6–7, pp. 2410–2414, 2018.
• [27] J. Pamina, T. Dhiliphan Rajkumar, S. Kiruthika, T. Suganya, and F. Femila, “Exploring hybrid and ensemble models for customer churn prediction in telecommunication sector,” Int. J. Recent Technol. Eng., vol. 8, pp. 299–309, 2019(b).
• [28] H. Jain, A. Khunteta, and S. Srivastava, “Telecom churn prediction and used techniques, datasets and performance measures: a review,” Telecommun. Syst., vol. 76, no. 4, pp. 613–630, 2021.
• [29] Seema & G.Gupta, “A critical examination of different models for customer churn prediction using data mining,” Int. J. Adv. Comput. Sci. Appl., vol. 8, no. 6S3, pp. 850-854, 2019.
• [30] R. Sudharsan, & E. N. Ganesh, “Churn rate prediction in telecommunication systems,” Int. J. Eng. Adv. Technol., vol. 8, no. 6, pp. 4720-4725, 2019.
• [31] Turkish Electronic Communications Industry, Quarterly Market Data Report, 2020, 3rd Quarter (Türkiye Elektronik Haberleşme Sektörü, Üç Aylık Pazar Verileri Raporu, 2020, 3. Çeyrek). Retrieved from https://www.btk.gov.tr/uploads/pages/pazar-verileri/uc-aylik-pazar-verileri-2020-3-kurumdisi.pdf
• [32] S. Moedjiono, Y. R. Isak, and A. Kusdaryono, “Customer loyalty prediction in multimedia service provider company with k-means segmentation and C4. 5 algorithm,” in 2016 International Conference on Informatics and Computing (ICIC), 2016, pp. 210–215.
• [33] C.-H. Chen, R.-D. Chiang, T.-F. Wu, and H.-C. Chu, “A combined mining-based framework for predicting telecommunications customer payment behaviors,” Expert Syst. Appl., vol. 40, no. 16, pp. 6561–6569, 2013.
• [34] M. C. Mozer, R. Wolniewicz, D. B. Grimes, E. Johnson, and H. Kaushansky, “Predicting subscriber dissatisfaction and improving retention in the wireless telecommunications industry,” IEEE Trans. Neural Networks, vol. 11, no. 3, pp. 690–696, 2000.
• [35] A. M. AL-Shatnwai and M. Faris, “Predicting customer retention using XGBoost and balancing methods,” Int. J. Adv. Comput. Sci. Appl., vol. 11, no. 7, pp. 704–712, 2020.
• [36] K. K.-K. Wong, “Getting what you paid for: Fighting wireless customer churn with rate plan optimization,” J. Database Mark. Cust. Strateg. Manag., vol. 18, no. 2, pp. 73–82, 2011.
• [37] S. F. Sabbeh, “Machine-learning techniques for customer retention: A comparative study,” Int. J. Adv. Comput. Sci. Appl., vol. 9, no. 2, 2018.
• [38] S. Mau, I. Pletikosa, and J. Wagner, “Forecasting the next likely purchase events of insurance customers: A case study on the value of data-rich multichannel environments,” Int. J. Bank Mark., 2018.
• [39] S. M. Kostić, M. I. Simić, and M. V Kostić, “Social network analysis and churn prediction in telecommunications using graph theory,” Entropy, vol. 22, no. 7, p. 753, 2020.
• [40] A. Amin et al., “Cross-company customer churn prediction in telecommunication:s A comparison of data transformation methods,” Int. J. Inf. Manage., vol. 46, pp. 304–319, 2019.
• [41] Y. Khan, S. Shafiq, A. Naeem, S. Hussain, S. Ahmed, and N. Safwan, “Customers churn prediction using artificial neural networks (ANN) in telecom industry,” Editor. Pref. From Desk Manag. Ed., vol. 10, no. 9, 2019.
• [42] P. Spanoudes and T. Nguyen, “Deep learning in customer churn prediction: unsupervised feature learning on abstract company independent feature vectors,” arXiv Prepr. arXiv1703.03869, 2017.
• [43] H. Faris, “A hybrid swarm intelligent neural network model for customer churn prediction and identifying the influencing factors,” Information, vol. 9, no. 11, p. 288, 2018.
• [44] Y. Zhang, J. Qi, H. Shu, and Y. Li, “Predicting churn probability of fixed-line subscriber with limited information: a data mining paradigm for enterprise computing,” in Research and Practical Issues of Enterprise Information Systems, Springer, pp. 589–590, 2006.
• [45] A. Mohd Khalid, I. Mohammad Ridwan, M. Mokhairi, A. R. M Nordin, and M. Abd Rasid, “Performance comparison of neural network training algorithms for modeling customer churn prediction,” Int. J. Eng. Technol, vol. 7, no. 2.15, pp. 35-37, 2017.
• [46] P. Wanchai, “Customer churn analysis: A case study on the telecommunication industry of Thailand,” in 2017 12th International Conference for Internet Technology and Secured Transactions (ICITST), 2017, pp. 325–331.
• [47] Y. Koçtürk, “Veri madenciliğinde bağlılık.” İstanbul Teknik Üniversitesi Fen Bilimleri Enstitüsü, 2010.
• [48] E. Kızılkaya Aydoğan, C. Gencer, and S. Akbulut, “Veri madenciliği teknikleri ile bir kozmetik markanın ayrılan müşteri analizi ve müşteri bölümlenmesi,” vol. 26, no. 1, Sigma Mühendislik ve Fen Bilimleri Dergisi, 2008.
• [49] I. Brânduşoiu, G. Toderean, and H. Beleiu, “Methods for churn prediction in the pre-paid mobile telecommunications industry,” in 2016 International conference on communications (COMM), 2016, pp. 97–100.
• [50] T. Kamalakannan and P. Mayilvaghnan, “Optimal customer relationship management in telecalling industry by using data mining and business intelligence,” Int. J. Eng. Technol., vol. 7, no. 1.1, pp. 12–17, 2018.
• [51] U. Özveren, “Pem yakıt hücrelerinin yapay sinir ağları ile modellenmesi,” Yıldız Teknik Üniversitesi, Fen Bilimleri Enstitüsü, 2006.
• [52] L. H. Tsoukalas and R. E. Uhrig, Fuzzy and neural approaches in engineering. John Wiley & Sons, Inc., 1996.
• [53] M. F. Keskenler and E. F. Keskenler, “Geçmişten günümüze yapay sinir ağları ve tarihçesi,” Tak. Vekayi, vol. 5, no. 2, pp. 8–18, 2017.
• [54] V. Gülpınar, “Yapay sinir ağları ve sosyal ağ analizi yardımı ile Türk Telekomünikasyon piyasasında müşteri kaybı analizi,” Marmara Üniversitesi İktisadi ve İdari Bilim. Derg., vol. 34, no. 1, pp. 331–350, 2013.
• [55] E. Alpaydin, Introduction to Machine Learning. MIT Press, 2020.
• [56] V. Vapnik, The Nature of Statistical Learning Theory. Springer Science & Business Media, 1999.
• [57] E. U. Küçüksille and N. Ateş, “Destek vektör makineleri ile yaramaz elektronik postaların filtrelenmesi,” Türkiye Bilişim Vakfı Bilgi. Bilim. ve Mühendisliği Derg., vol. 6, no. 1, 2013.
• [58] O. Kaynar, M. F. Tuna, Y. Görmez, and M. A. Deveci, “Makine öğrenmesi yöntemleriyle müşteri kaybı analizi,” Cumhur. Üniversitesi İktisadi ve İdari Bilim. Derg., vol. 18, no. 1, pp. 1–14, 2017.
• [59] L. Breiman & A. Cutler, Random Forest, Retrieved from http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm
• [60] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001.
• [61] M. Pal, “Random forest classifier for remote sensing classification,” Int. J. Remote Sens., vol. 26, no. 1, pp. 217–222, 2005.
• [62] A. Liaw and M. Wiener, “Classification and regression by randomForest,” R news, vol. 2, no. 3, pp. 18–22, 2002.
• [63] M. Skurichina and R. P. W. Duin, “Bagging, boosting and the random subspace method for linear classifiers,” Pattern Anal. Appl., vol. 5, no. 2, pp. 121–135, 2002.
• [64] Telco Customer Churn Focused customer retention programs data set, [Online]. Available: https://www.kaggle.com/blastchar/telco-customer-churn
• [65] Y. Beeharry and R. Tsokizep Fokone, “Hybrid approach using machine learning algorithms for customers’ churn prediction in the telecommunications industry,” Concurr. Comput. Pract. Exp., vol. 34, no. 4, 2022
• [66] S. Halibas, A. Cherian Matthew, I. G. Pillai, J. Harold Reazol, E. G. Delvo, and L. Bonachita Reazol, “Determining the intervening effects of exploratory data analysis and feature engineering in telecoms customer churn modelling,” 2019 4th MEC Int. Conf. Big Data Smart City, ICBDSC 2019, 2019
• [67] N. Tamuka and K. Sibanda, “Real Time Customer Churn Scoring Model for the Telecommunications Industry,” 2020 2nd Int. Multidiscip. Inf. Technol. Eng. Conf. IMITEC 2020, 2020.
• [68] Y. Beeharry and R. Tsokizep Fokone, “Hybrid approach using machine learning algorithms for customers’ churn prediction in the telecommunications industry,” Concurr. Comput. Pract. Exp., vol. 34, no. 4, 2022.
• [69] N. I. Mohammad, S. A. Ismail, M. N. Kama, O. M. Yusop, and A. Azmi, “Customer Churn Prediction in Telecommunication Industry Using Machine Learning Classifiers,” ACM Int. Conf. Proceeding Ser., 2019
• [70] N.V. Raut, “A Study of Ensemble Machine Learning to Improve Telecommunication Customer Churn Prediction,” Dissertation submitted in part fulfilment of the requirements for the degree of MSc Data Analytics At Dublin Business School, pp. 1–52.
• [71] L. Hota and K. Dash, “55_Prediction of Customer Churn in Telecom Industry: A Machine Learning Perspective,” Comput. Intell. Mach. Learn., vol. 2, no. 2, pp. 1–9, 2021.
• [72] M. Makruf, A. Bramantoro, H. J. Alyamani, S. Alesawi, and R. Alturki, “Classification methods comparison for customer churn prediction in the telecommunication industry,” Int. J. Adv. Appl. Sci., vol. 8, no. 12, 2021.
• [73] D. R . Chabumba, A. Jadhav, and Ajoodha, R. (2021), “Predicting telecommunication customer churn using machine learning techniques,” In Interdisciplinary Research in Technology and Management, pp. 625-636). CRC Press.
• [74] P. Lalwani, M. K. Mishra, J. S. Chadha, and P. Sethi, “Customer churn prediction system: a machine learning approach,” Computing, vol. 104, no. 2, pp. 271–294, 2022.