پیش‌بینی احتمال رویگردانی مشتریان در صنعت بانکداری ایران مورد مطالعه: یک بانک خصوصی ایرانی

نوع مقاله: مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری مدیریت فناوری اطلاعات، دانشکده مدیریت و حسابداری، دانشگاه علامه طباطبائی، تهران، ایران

2 دانشیار گروه مدیریت فناوری اطلاعات، دانشکده مدیریت و حسابداری، دانشگاه علامه طباطبائی

3 دانشیار گروه مدیریت فناوری اطلاعات، دانشکده مدیریت و حسابداری، دانشگاه علامه طباطبائی، تهران، ایران،

چکیده

پس از ظهور بانک‌های خصوصی در ایران به دلیل جذابیت صنعت شاهد رشد سریع تعداد این نوع بانک‌ها و فشار رقابتی بالای این صنعت در کشور هستیم. ریزش مشتریان از یک بانک به معنی کاهش منابع بانک بوده و با توجه به هزینه‌های بالاتر جذب مشتریان نسبت به نگهداری آن‌ها، بانک‌ها به شدت تلاش می‌کنند که مشتریان خود را حفظ کنند. لذا محاسبه احتمال رویگردانی مشتریان با بررسی رفتار مالی آن‌ها و در صورت امکان جلوگیری از ریزش آن‌ها بسیار کلیدی است.  در این مقاله با استفاده از تکنیک داده‌کاوی خوشه‌بندی سلسه‌مراتبی برای تشخیص مشتریان از منظر رویگردانی و همچنین زنجیره احتمالات مارکوف برای تعیین احتمال رویگردانی در آینده، مدلی ساخته شده است که از طریق یادگیری داده‌های رفتار مالی مشتریان بتواند احتمال ریزش مشتری را پیش‌بینی کند. این مدل روی یک سال داده‌های واقعی تراکنش‌های سپرده‌های کوتاه‌مدت روزشمار و قرض‌الحسنه جاری در یک بانک خصوصی ایرانی پیاده شد. نتایج نشان داد در صورتی که بانک مشتری را از دست بدهد احتمال بازگرداندن مشتری بسیار پایین است. همچنین مشتریان فعال که معمولاً با هزینه‌های بالا جذب بانک می‌شوند، بسیار ناپایدار هستند و به سرعت تغییر وضعیت می‌دهند. البته در صورتی که مشتری فعال از دست نرود فرصت محدودی از نظر زمانی برای بانک‌ها جهت فعال‌سازی دوباره مشتریان وجود دارد.

کلیدواژه‌ها


عنوان مقاله [English]

Churn Prediction in Iran Banking Industry Case of a Private Iranian Bank

نویسندگان [English]

  • Mohsen Asgari 1
  • Mohammadreza Taghva 2
  • Mohammadtaghi Taghavifard 3
1 Ph.D Candidate, Faculty of management and accounting, Allameh Tabataba’I University, Tehran, Iran
2 Prof, Faculty of management and accounting, Allameh Tabataba’I University, Tehran
3 Prof, Faculty of management and accounting, Allameh Tabataba’I University, Tehran, Iran,
چکیده [English]

Abstract
After the emergence of private banks in Iran, due to its attractiveness, this industry has witnessed a rapid growth such banks. The abundance of private banks led to a very high pressure competitive environment and gave dissatisfied customers a chance to easily switch banks. On the other hand, the most important advantage of the competitive environment among the banks is to have more resources at a low risk. Losing customers to another bank is equivalent to a decrease in a bank's resources. Since the acquisition of new customers, costs much more in comparison to maintaining the existing ones, the banks try hard to keep their customers. Thus, customers churn predictions via analyzing their financial behavior and finding possible methods for preventing customer defection is crucial. This research utilizes the hierarchical K-means clustering technique for detection of customers’ churn and also applies Markov Chain model for calculating the probability of customer churning in the future. Using these techniques and financial data of an Iranian private bank, we build an example of this model that can predict the possibility of losing customers.
Introduction
Tough competition in the Iranian banking industry, especially among private banks, has forced them to pay more attention to customer relationship management. Because of the higher cost of customer acquisition compared to customer retention, banks try hard to preserve their customers. Customer churn prediction can help a bank to predict its customers’ intention to stop using bank’s services. This can be done by using the customers’ transaction data with the help of data mining techniques. Also, this prediction can help banks reduce the risk of deposit resource loss which is very important in banking business. Therefore, the main purpose of this study is to build a churn prediction model suitable for the Iranian banking industry.
Research Methodology
In this study a data set consisting of financial transactions of 385,912 customers of an Iranian private bank in a one-year period is used. For the purposes of churn detection, we first used a hierarchical K-means clustering on some churn-related parameters. Then, with the help of 11 experts we ranked the clusters by degree of churn. This ranking is done by comparing every two clusters from a churn perspective with the help of the experts. After that we group the clusters in 4 states of churn: Active, Steady, Churning and Churned. If a customer belongs to the Active state, it means that his/her behavior is just opposite of churning. When customers move to the next states from Steady to Churning and Churned, their behavior is more like churning. Then, we calculate the transition of customers between states through time. Finally, using a Markov chain technique we build a model that can predict the customers churn state change.
Findings
We calculate the three parameters of Recency, Frequency and Monetary for each customer.  Based on these parameters the customers are clustered into ten clusters. The clusters are then grouped in four states of churn: Active, Steady, Churning, Churned. By determining the transitions of customers between these four states we build a Markov chain model. In order to determine the transitions, we use the states of customers in the first seven months of data compared to their states in the next five months.
Discussion
Most of the customers who belong to cluster number 18 and are in the Steady state of churn are not much active in the bank. The probabilities of state transitions indicate that 79 percent of customers who are in the Churned state will not change their state. This means that if a bank loses its customers, then there is very little opportunity to win them back. Therefore, the decision makers in the bank should try hard to prevent a customer, particularly one in Churning state, to go to the Churned state.
About 74 percent of customers in Active state will go to Steady state. If nothing happens, most of the customers who are active will be steady after sometime. The probability that a customer in Active state keeps his/her state is a little more than 12 percent. So the active customers are very unstable. However, the probability of a customer going from the Steady state to the Active state is around 39 percent.  Hence, there is an opportunity for the banks to focus on customers in Steady state and give them incentives to persuade them to be more active.
The probability that a customer changes his/her state from Steady to Churning is around 20 percent. This means that in normal conditions 20 percent of customers that are in Steady state will go to Churning state. So it is very crucial for the banks to be more focused on customers in the Steady. In another words, the key state to focus on is the Steady state and if the banks give incentives to these customers they will not change their state to Churning.
The probability of getting a customer in the Churned state back to the Steady state is around one percent. So, it is very hard for a bank to win back a customer who has churned. The decision makers are well advised to have customer relationship plans to prevent customers from going to the Churned state. If this happens, however, there will be very little they can do to have them go back.
The model can help bank decision makers select some customers to pay more attention to. With the help of giving some incentives in the form of customer loyalty programs, banks can survive the loss of customers.

کلیدواژه‌ها [English]

  • Churn Prediction
  • Banking
  • Markov Model
  • Hierarchical K-Means
  • Data Mining
1-Ali, Ö. G., & Arıturk, U. (2014). Dynamic churn prediction framework with more effective use of rare event data: The case of private banking. Expert Systems with Applications, 41(17), 7889-7903.

2-Anil Kumar, D., & Ravi, V. (2008). Predicting credit card customer churn in banks using data mining. international journal of data analysis techniques and strategies, 1(1), 4-28.

3-Babu, S., & Ananthanarayanan, N. R. (2018). Enhanced Prediction Model for Customer Churn in Telecommunication Using EMOTE. In International Conference on Intelligent Computing and Applications (pp. 465-475). Springer, Singapore.

4-Buckinx, W., & Van den Poel, D. (2005). Customer base analysis: partial defection of behaviourally loyal clients in a non-contractual FMCG retail setting. European Journal of Operational Research, 164(1), 252-268.

5-Caigny, A., Coussement, K., & De Bock, K. W. (2018). A new hybrid classification algorithm for customer churn prediction based on logistic regression and decision trees. European Journal of Operational Research, 269(2), 760-772.

6-Chiang, D. A., Wang, Y. F., Lee, S. L., & Lin, C. J. (2003). Goal-oriented sequential pattern for network banking churn analysis. Expert Systems with Applications, 25(3), 293-302.

7-Chitra, K., & Subashini, B. (2011). Customer retention in banking sector using predictive data mining technique. In ICIT 2011 The 5th International Conference on Information Technology.

8-Coussement, K., & De Bock, K. W. (2013). Customer churn prediction in the online gambling industry: The beneficial effect of ensemble learning. Journal of Business Research, 66(9), 1629-1636.

9-Coussement, K., Lessmann, S., & 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.

10-Dahiya, K., & Bhatia, S. (2015, September). Customer churn analysis in telecom industry. In Reliability, Infocom Technologies and Optimization (ICRITO)(Trends and Future Directions), 2015 4th International Conference on (pp. 1-6). IEEE.

11-Farquad, M. A. H., Ravi, V., & Raju, S. B. (2014). Churn prediction using comprehensible support vector machine: An analytical CRM application. Applied Soft Computing, 19, 31-40.

12-Farquad, M. A. H., Ravi, V., & Raju, S. B. (2009, December). Data mining using rules extracted from SVM: an application to churn prediction in bank credit cards. In International Workshop on Rough Sets, Fuzzy Sets, Data Mining, and Granular-Soft Computing (pp. 390-397). Springer, Berlin, Heidelberg.

13-Gunther, C. C., Tvete, I. F., Aas, K., Sandnes, G. I., & Borgan, Ø. (2014). Modelling and predicting customer churn from an insurance company. Scandinavian Actuarial Journal, 2014(1), 58-71.

14-Huang, Y., & Kechadi, T. (2013). An effective hybrid learning system for telecommunication churn prediction. Expert Systems with Applications, 40(14), 5635-5647.

15-Kaur, M., Singh, K., & Sharma, N. (2013). Data Mining as a tool to Predict the Churn Behaviour among Indian bank customers. International Journal on Recent and Innovation Trends in Computing and Communication, 1(9), 720-725.

16-Kazemi, M., & Hejazinia, R. (2017). Study affective variables in mobile customers’ churn. Journal of Development Evolution Management, 7, 115-121. (In Persian)

17-Khashei, M., & Bijari, M. (2012). A new class of hybrid models for time series forecasting. Expert Systems with Applications, 39(4), 4344-4357.

18-Kim, K., Jun, C. H., & Lee, J. (2014). Improved churn prediction in telecommunication industry by analyzing a large network. Expert Systems with Applications, 41(15), 6575-6584.

19-Kim, Y. S., Lee, H., & Johnson, J. D. (2013). Churn management optimization with controllable marketing variables and associated management costs. Expert Systems with Applications, 40(6), 2198-2207.

20-Lu, N., Lin, H., Lu, J., & Zhang, G. (2014). A customer churn prediction model in telecom industry using boosting. IEEE Transactions on Industrial Informatics, 10(2), 1659-1665.

21-Mirmohammadi, SM., & Ghanei, H., & Keramati, A. (2015). Customer Churn Prediction Using Decision Tree Method in Electronic Banking Industry (Case Study: Ansar Bank).  Journal of Development in Monetary and Banking Management, 3(6), 1-30. (In Persian)

22-Oyeniyi, A. O., Adeyemo, A. B., Oyeniyi, A. O., & Adeyemo, A. B. (2015). Customer churn analysis in banking sector using data mining techniques. Afr J Comput ICT, 8(3), 165-174.

23-Popovic, D., & Basic, B. D. (2009). Churn prediction model in retail banking using fuzzy C-means algorithm. Informatica, 33(2).

24-Prasad, U. D., & Madhavi, S. (2012). Prediction of churn behavior of bank customers using data mining tools. Business Intelligence Journal, 5(1), 96-101.

25-Rezaei Navaei, S., & Koosha, H. (2016). Applying Data Mining Techniques for Customer Churn Prediction in Insurance Industry. International Journal of Industrial Engineering & Production Management, 27(4), 635-653. (In Persian)

26-Riebe, E., Wright, M., Stern, P., & Sharp, B. (2014). How to grow a brand: Retain or acquire customers?  Journal of Business Research, 67(5), 990-997.

Tsai, C. F., & Lu, Y. H. (2009). Customer churn prediction by hybrid neural networks. Expert Systems with Applications, 36(10), 12547-12553.

27-Verbeke, W., Dejaeger, K., Martens, D., Hur, J., & Baesens, B. (2012). New insights into churn prediction in the telecommunication sector: A profit driven data mining approach. European Journal of Operational Research, 218(1), 211–229

28-Vafeiadis, T., Diamantaras, K. I., Sarigiannidis, G., & Chatzisavvas, K. C. (2015). A comparison of machine learning techniques for customer churn prediction. Simulation Modelling Practice and Theory, 55, 1-9.

29-Xie, Y., Li, X., Ngai, E. W. T., & Ying, W. (2009). Customer churn prediction using improved balanced random forests. Expert Systems with Applications, 36(3), 5445-5449.

30-Yang, C., Shi, X., Luo, J., & Han, J. (2018). I Know You’ll Be Back: Interpretable New User Clustering and Churn Prediction on a Mobile Social Application.

31-Zhu, B., Xiao, J., & He, C. (2014). A Balanced Transfer Learning Model for Customer Churn Prediction. In Proceedings of the Eighth International Conference on Management Science and Engineering Management (pp. 97-104). Springer, Berlin, Heidelberg.

32-Zhu, B., Baesens, B., Backiel, A. E., & vanden Broucke, S. K. (2018). Benchmarking sampling techniques for imbalance learning in churn prediction. Journal of the Operational Research Society, 69(1), 49-65.

33-Zoric, B. A. (2016). Predicting customer churn in banking industry using neural networks. Interdisciplinary Description of Complex Systems: INDECS, 14(2), 116-124.