پیش بینی رویگردانی مشتریان بانک با استفاده از روش داده کاوی
محورهای موضوعی :
مدیریت صنعتی
parvin najmi
1
,
abbas rad
2
,
maryam shoar
3
1 - Tehran North branch, Islamic Azad University, Tehran, Iran
2 - Assistant Professor, Faculty of Management, Shahid Beheshti University
3 - Dr. Maryam Shahram Assistant Professor, Faculty of Management, Islamic Azad University, Tehran North
تاریخ دریافت : 1397/02/10
تاریخ پذیرش : 1397/08/11
تاریخ انتشار : 1397/06/01
کلید واژه:
شبکه عصبی,
درخت تصمیم,
ماشین بردار پشتیبان,
نقشه خود سازمان ده,
مشتری رویگردان,
چکیده مقاله :
شدت رقابت درفضای صنعتی ، باعث شده است که تمایل بنگاه‌های اقتصادی به جذب مشتریان بیشتر کم و، تمایل به فعالیت در زمینه‌های خدماتی و تولیدی افزایش یافته است. به همین منظور، توسعه روش هایی به منظور شناسایی مشتریان رویگردان و پیش بینی رویگردانی، از مهمترین فعالیت های حوزه فروش به حساب خواهد آمد. در صورتی که بانک فرصت کافی برای پیش بینی رویگردانی مشتریان داشته باشد؛ می تواند به اصلاح ساختارها و خدمات خود به منظور جلوگیری از ریزش تعداد بیشتری از مشتریان بپردازد. تحقیق حاضر، به منظور توسعه چنین مدلی برای بانک شهر صورت گرفته است. به همین منظور، از یک الگوریتم دو مرحله ای خوشه بندی، دسته بندی داده کاوی استفاده شده. به منظور خوشه بندی مشتریان، از نقشه های خودسازمان ده شبکه عصبی که یک روش یادگیری نظارت نشده است؛ استفاده و برای دسته بندی از ماشین بردار پشتیبان و درخت تصمیم استفاده شده است. روش استفاده از این ابزارها به این صورت است که ابتدا از دو مشخصه میانگین موجودی و میانگین تراکنش مشتریان در دوره سه ماهه پایانی استفاده شده و به عنوان ورودی شبکه عصبی در خوشه بندی مورد استفاده قرار گرفته است. پس از آن، در مرحله کلاس بندی، از داده های مربوط به تراکنش های نقدی و اعتباری به منظور کلاس بندی و پیش بینی استفاده شده است. نتایج به دست آمده حاکی از آن است که مدل پیشنهادی بیش از 80% توانایی پیش بینی رویگردانی مشتری را داشته و ماشین بردار پشتیبان عملکرد بهتری از درخت تصمیم نشان داده است.
چکیده انگلیسی:
The intensity of finding competition in the industrial and economic space and the market move towards a complete competition market has made the inclination of firms to attract more customers and, instead, have increased the tendency to operate in various service and manufacturing areas. This policy, which is known for increasing the share of wallet, makes it more important to maintain customer relationships and analyze their relationships, and it is necessary to conduct customer behavioral analysis, customer relationship analysis, and customer behavior forecasting. The present research seeks to identify customers who are turning away and anticipates the decline of customers in order to prevent customers from falling. In this regard, the variables associated with the reversal analysis are first identified and then the bank customers are clustered using a neural network and classified into three categories of loyal, regular, and negative clients. With the receipt of the above labels, a backup vector machine has been used to classify and reverse prediction. Based on the results, the proposed method has the ability to predict rotational deviation of up to 80% and, moreover, has a better performance than the classical decision tree.
منابع و مأخذ:
Adwan, Omar et al. (2014). Predicting customer churn in telecom industry using multilayer perception neural networks: Modeling and analysis. Life Science Journal,11(3): 75-81.
Amir Shahi, Mirahmad, Siahtiri, Vida, Ravanbod, Fariba. (2010). Identifying the factors affecting the creation of “trust” in key bank customers: key customers of the Bank of Entrepreneur in Tehran. Management Researches in Iran, 4(64): 61-67.
Haghighi Kafash, Mehdi, & Akbari, Masoud. (2011).Prioritizing Factors Affecting Customer Loyalty Using the ECSI Model. Marketing Management, 6 (10): 95-118.
Bahramzadeh, Mohammad Mehdi, Shokati Maghareb, Somayeh. (2010). Identification and ranking of factors affecting customer loyalty in private banks of Khuzestan province. Second International Financial Services Marketing Conference.
Castanedo, Federico, et al. (2014). Using deep learning to predict customer churn in a mobile telecommunication network.
Datta, P., Masand, B., Mani, D., & Li, B. (2000). Automated cellular modeling and prediction on a large scale. Artificial Intelligence Review, 14: 485–502.
Ghanbarterani, Nasim. (2014). Customer clustering based on RFM model and data mining approach to increase customer loyalty. MSc Thesis, Tarbiat Moalem University, Faculty of Engineering.
Gordini, Niccolò, and Valerio, Veglio. (2017). Customers churn prediction and marketing retention strategies: An application of support vector machines based on the auc parameter-selection technique in b2b e-commerce industry. Industrial Marketing Management, 62: 100-107.
Huang, Bingquan et al. (2016). A Fuzzy Rule-Based Learning Algorithm for Customer Churn Prediction. Industrial Conference on Data Mining. Springer International Publishing, 2016.
Huigevoort, Chantine, and Remco, Dijkman. (2015). Customer churn prediction for an insurance company. Diss. M. Sc. Thesis, Eindhoven University of Technology, Eindhoven, Netherland, 2015.
Lee, W. S., Tzeng, G. H., Guan, J. L., Chein, K. T., and Huang, J. M. (2009). Combined MCDM Techniques for Exploring Stock Selection Based on Gordon Model. Expert Systems with Applications, 36(7): 6421-6430.
Mutanen, Teemu. (2006). Customer churn analysis–a case study. Journal of Product and Brand Management, 14(1): 4-13.
Óskarsdóttir, María, et al. (2016). A comparative study of social network classifiers for predicting churn in the telecommunication industry. Advances in Social Networks Analysis and Mining (ASONAM), 2016 IEEE/ACM International Conference on. IEEE.
Prasad, U. Devi, and S. Mahdavi. (2012). Prediction of churn behavior of bank customers using data mining tools. Business Intelligence Journal5(1): 96-101.
Sharma, Anuj, Panigrahi, and Prabin Kumar. (2013). A neural network based approach for predicting customer churn in cellular network services. Ar Xiv preprint Ar Xiv:1(309):39-45.
Vafeiadis, Thanasis et al. (2015). A comparison of machine learning techniques for customer churn prediction. Simulation Modeling Practice and Theory,55: 1-9.
Vapnik, Viladmir, N. (1998). An overview of statistical learning theory. John Wiley & Sons Inc., New York.
Zhang, L., and Zhou, W. D. (2011). Density-Induced Margin Support Vector Machines. Pattern Recognition, 44(8): 1448-1460.
_||_
Adwan, Omar et al. (2014). Predicting customer churn in telecom industry using multilayer perception neural networks: Modeling and analysis. Life Science Journal,11(3): 75-81.
Amir Shahi, Mirahmad, Siahtiri, Vida, Ravanbod, Fariba. (2010). Identifying the factors affecting the creation of “trust” in key bank customers: key customers of the Bank of Entrepreneur in Tehran. Management Researches in Iran, 4(64): 61-67.
Haghighi Kafash, Mehdi, & Akbari, Masoud. (2011).Prioritizing Factors Affecting Customer Loyalty Using the ECSI Model. Marketing Management, 6 (10): 95-118.
Bahramzadeh, Mohammad Mehdi, Shokati Maghareb, Somayeh. (2010). Identification and ranking of factors affecting customer loyalty in private banks of Khuzestan province. Second International Financial Services Marketing Conference.
Castanedo, Federico, et al. (2014). Using deep learning to predict customer churn in a mobile telecommunication network.
Datta, P., Masand, B., Mani, D., & Li, B. (2000). Automated cellular modeling and prediction on a large scale. Artificial Intelligence Review, 14: 485–502.
Ghanbarterani, Nasim. (2014). Customer clustering based on RFM model and data mining approach to increase customer loyalty. MSc Thesis, Tarbiat Moalem University, Faculty of Engineering.
Gordini, Niccolò, and Valerio, Veglio. (2017). Customers churn prediction and marketing retention strategies: An application of support vector machines based on the auc parameter-selection technique in b2b e-commerce industry. Industrial Marketing Management, 62: 100-107.
Huang, Bingquan et al. (2016). A Fuzzy Rule-Based Learning Algorithm for Customer Churn Prediction. Industrial Conference on Data Mining. Springer International Publishing, 2016.
Huigevoort, Chantine, and Remco, Dijkman. (2015). Customer churn prediction for an insurance company. Diss. M. Sc. Thesis, Eindhoven University of Technology, Eindhoven, Netherland, 2015.
Lee, W. S., Tzeng, G. H., Guan, J. L., Chein, K. T., and Huang, J. M. (2009). Combined MCDM Techniques for Exploring Stock Selection Based on Gordon Model. Expert Systems with Applications, 36(7): 6421-6430.
Mutanen, Teemu. (2006). Customer churn analysis–a case study. Journal of Product and Brand Management, 14(1): 4-13.
Óskarsdóttir, María, et al. (2016). A comparative study of social network classifiers for predicting churn in the telecommunication industry. Advances in Social Networks Analysis and Mining (ASONAM), 2016 IEEE/ACM International Conference on. IEEE.
Prasad, U. Devi, and S. Mahdavi. (2012). Prediction of churn behavior of bank customers using data mining tools. Business Intelligence Journal5(1): 96-101.
Sharma, Anuj, Panigrahi, and Prabin Kumar. (2013). A neural network based approach for predicting customer churn in cellular network services. Ar Xiv preprint Ar Xiv:1(309):39-45.
Vafeiadis, Thanasis et al. (2015). A comparison of machine learning techniques for customer churn prediction. Simulation Modeling Practice and Theory,55: 1-9.
Vapnik, Viladmir, N. (1998). An overview of statistical learning theory. John Wiley & Sons Inc., New York.
Zhang, L., and Zhou, W. D. (2011). Density-Induced Margin Support Vector Machines. Pattern Recognition, 44(8): 1448-1460.
