دسته‌بندی سرویس‌های‌ مشتریان به لحاظ سطح استفاده از خدمات شبکه شتاب با استفاده از مدل‌های ترکیبی

نوع مقاله: مقاله پژوهشی

نویسندگان

1 گروه مهندسی کامپیوتر ـ دانشگاه آزاد اسلامی واحد الکترونیک ـ تهران ـ ایران

2 گروه مهندسی کامپیوتر، واحد شهرقدس، دانشگاه آزاد اسلامی، تهران، ایران

چکیده

با تجهیز بانک‌ها به سیستم‌های پرداخت و دریافت الکترونیکی و استفاده از کارت‌‌های اعتباری، مشتریان اکثر تعاملات بانکی خود را از طریق کارت‌‌های اعتباری و کانال‌‌های اعتباری نظیر دستگاه‌‌های خودپرداز ATM، پایانه‌‌های فروش POS، تلفن‌بانک، موبایل بانک و اینترنت بانک انجام می‌دهند. مشتریان با افزایش تعداد بانک‌ها و محصولات و خدمات آنان، زمانی که خدمات و محصولات بهتری پیدا کنند، به‌راحتی بانک خود را تغییر می‌دهند؛ بنابراین، مدیریت ارتباط با مشتری یک انتخاب اجتناب‌ناپذیر برای بانک‌هاست. یکی از ابزار‌هایی که در‌ زمینه مدیریت ارتباط با مشتری می‌تواند به سازمان‌ها کمک‌کننده باشد، داده‌کاوی است. در این تحقیق برای شناسایی خدمات سودآوری که توسط مشتریان خوب مورد استقبال قرار گرفته‌اند، چهار روش داده‌کاوی درخت تصمیم، بیز ساده، K همسایه نزدیک و مدل ترکیبی استفاده شدند. هر یک از این روش‌ها بر روی داده‌های واقعی، آزمایش و کارایی هر روش سنجیده شد. نتایج ارزیابی مدل‌ها نشان داد که دقت مدل K همسایه نزدیک در شناسایی خدمات سودآور 26/93 درصد، دقت مدل بیز 83/74 درصد و دقت مدل درخت تصمیم 18/97 درصد است و پس از ترکیب مدل‌ها، دقت روش ترکیبی80/94 درصد شده است. همچنین مدل ترکیبی 01/96 درصد از خدمات عادی را درست شناسایی کرده و در مجموع 44/94 درصد از خدمات را به‌درستی تشخیص داده است و عملکرد بهتری نسبت به روش بیز ساده و K همسایه نزدیک داشته است. از مقایسه نتایج ارزیابی مدل‌ها مشخص شد که استفاده از روش‌های ترکیبی در مقایسه با روش‌های دسته‌بندی مبتنی بر یک مدل، از دقت بیشتری برخوردار است.

کلیدواژه‌ها


عنوان مقاله [English]

Classification of Customer Services in Terms of the Use of Shetab Network Services Based on Ensemble Classification

نویسندگان [English]

  • Shahrzad Behnaz 1
  • Rahil Hosseini 2
1 Department of Department of Computer Engineering and Information Technology, School of Faculty of Engineering and Technology, Branch Islamic Azad University E-Campus, Tehran, Iran.
2 Department of Computer Engineering, Shahr-e-Qods Branch, Islamic Azad University Tehran, Iran
چکیده [English]

Upon equipping the banks to Electronic payment and receiving systems as well as the use of credit cards, most of the customers do their bank transactions by using credit cards and through the use of credit channels such as ATM machines, POS sale terminals, phone banking, internet banking, etc. The customers are now better able to find their required services and products and they may even change their own bank because of the type of services required. Therefore, managing customer relations is inevitable for banks. One of the helpful instruments in managing customer relations is data mining. Four data mining methods including decision tree, simple Biz, Vicinity neighbor K and combinatory model were used in this study to identify the most profitable services used by the customers. Each of these methods has been investigated on real data and the efficiency of each method has been examines. The results of model evaluations showed that vicinity neighbor K’s accuracy in finding the profitable services was equal to 93.26%, that of Biz was 74.83% and that of decision tree was 97.18%. in addition, the accuracy of combinatory model was 94.80%. Further, the combinatory model was successful in accurately identifying 96.01% of the normal services and it was also successful to accurately identify 94.44% of the services. Therefore, we may conclude that it has a far better performance as compared with Biz model and Vicinity Neighbor K. the evaluations results showed that combinatory model is more accurate to use as compared with other existing models.

کلیدواژه‌ها [English]

  • Ensemble Classification
  • Bayse Classifier
  • Decision tree
  • KNN
  • Voting
Jamal Shahrabi, Esmaeil Hadavandi, Data mining in the banking industry, Amirkabir University of Technology Branch, 2011, pp. 8-71.

[2] Ravichandran, S. S., et al., Rule-base data mining systems for customer queries, Computing Communication & Networking Technologies (ICCCNT), 2012 Third International Conference on, IEEE, 2012.

[3] Mohammad Taghi Taghavifard, Reza Habibi, Hamed Abdolahi, Determination of bank survivability and profitability using decision tree and regression forest model, Journal of Modern Researches in Decision Making vol. 2, no. 4, 2017, pp. 58-79.

[4] Mostafa Esmaeili, Behrouz Minaei, Bank customer analysis based on the amount of activity in the accelerated network using data mining techniques, Information Technology Management Conference Shahid Beheshti University, 2015.

 [5] XI, Y.-p. and C. Min, Application of Data Mining Technology in CRM System of Commercial Banks, DEStech Transactions on Engineering and Technology Research (eeta), 2017.

[6] Çaliş, A., Data mining application in banking sector with clustering and classification methods, Industrial Engineering and Operations Management (IEOM), 2015 International Conference on, IEEE, 2015.

[7] Bahari, T. F. and M. S. Elayidom, An efficient CRM-data mining framework for the prediction of customer behaviour. PROCedia Computer Science 46: pp. 725-731, 2015.

[8] Shakouri, H., Presenting a model for predicting needed technologies in banks using SOM and ARM, Knowledge & Technology, in Press, 2016.

[9] Sajad Shokouhyar, Ali Otarkhani, Prediction of the behavior of e-banking customers by using data mining methods (Case study: Bank of the city), International Conference on Management and Economic Development, 2016.

[10] Maryam Sadat Motahari, designing a Model to Improve Banking Systems Based on Predicting Customer Interests: Using Data Mining Methods, Journal of Information Technology Management Vol. 8, no. 2, 2017, pp. 393-414.

[11]Mitik, M., Data Mining Based Product Marketing Technique for Banking Products,. Data Mining Workshops (ICDMW), 2016 IEEE 16th International Conference on, IEEE, 2016.

[12] Azim Zarei, Designing a Structural Model for Customer Disruption in Public Banks (Case study: Selected Banks of Semnan), Journal of  Management Research in Iran vol. 21, no. 1, 2017.
[13] Han, J., et al., Data mining: concepts and techniques, Elsevier, 2011.

[14] Seyed Alireza Mousavi Bashiri, Amir Afsar and Arash Mahjubi Fard, Analysis of customer value in the bank using data mining technique and fuzzy hierarchical analysis, Journal of  Management Research in Iran vol.19,no1,2015,pp.23-43
[15] "Concepts, Definitions and Methods", the website of the Central Bank of the Islamic Republic of Iran, available on 15/7/1397, available at the link: https://www.cbi.ir/simplelist/4505.aspx