پیش‌بینی پاسخ مشتریان در بازاریابی مستقیم با شبکه‌های عصبی چندلایه

نوع مقاله: مقاله پژوهشی

نویسندگان

1 استادیار، گروه مدیریت بازرگانی، واحد قزوین، دانشگاه آزاد اسلامی، قزوین، ایران

2 دانشیار، گروه مدیریت بازرگانی، دانشکدة مدیریت و حسابداری، دانشگاه آزاد اسلامی، واحد تهران مرکزی، تهران، ایران

3 دانشیار، گروه مدیریت صنعتی، دانشکدة مدیریت و حسابداری، دانشگاه آزاد اسلامی، واحد تهران مرکزی، تهران، ایران

چکیده

هدف پژوهش حاضر شناسایی هر چه دقیق‌تر مشتریان بالقوه جهت مخاطب قرار دادن در برنامه‌های بازاریابی مستقیم است که از دیرباز به عنوان یکی از مسائل مهم و مورد علاقة بازاریابان شیوة مستقیم مطرح بوده است. مهم‌ترین مسئله در این راستا کاوش در مجموعة داده‌های مشتریان است که همواره از عدم توازن بالایی برخوردار می‌باشد. در این پژوهش با ترکیب روش‌های کم نمونه‌گیری و بیش‌نمونه‌گیری تصادفی کلاس اکثریت و اقلیت که در پژوهش‌های گذشته به کرات استفاده شده، با خوشه‌بندی مشتریان و استخراج نمونه‌‌های متعادل‌تر اقدام به طراحی و توسعه یک الگوریتم پویا و اثربخش در راستای شناسایی و پیش‌بینی مشتریان بالقوه نموده‌ایم. بدین‌منظور از پایگاه دادة مشتریان یک آژانس مسافرتی (بالغ بر 10000 رکورد) استفاده شده است. نتایج حاکی از آن است که با استفاده از داده‌های اولیه مشتریان به هیچ وجه نمی‌توان به یک پیش‌بینی قابل اتکا و استفاده دست‌یافت. بکارگیری روش‌های نمونه‌گیری مجدد با استفاده از خوشه‌بندی مشتریان و ترکیب کلاس‌های اقلیت و اکثریت به روش‌های مختلف و مطابق با الگوریتم ابتکاری ارائه شده می‌تواند توان پیش‌بینی طبقه‌بند درخت‌ تصمیم را به طرز شگفت‌انگیزی افزایش داده و در موقعیت‌ها و بازارهای مختلف مورد استفاده قرار گیرد. در نهایت با ترکیب نتایج حاصل از کدهای XML استخراج شده در هر مرحله و معیار «حاصل‌ضرب» می‌توان به شناسایی و رتبه‌بندی مشتریان بالقوه و هدف‌گذاری آنها به شیوه‌ای کارآمد پرداخت.

کلیدواژه‌ها


عنوان مقاله [English]

Improvement of customer response prediction in direct marketing by neural networks

نویسندگان [English]

  • Mehdi Zakipour 1
  • Sina Nematizadeh 2
  • Mohamdali Afsharkezemi 3
1 Department of Business Management, Qazvin Branch, Islamic Azad University, Qazvin, Iran
2 Associate Professor, Faculty of Management and Accounting, Islamic Azad University, Central Tehran Branch, Tehran, Iran
3 Associate Professor, Faculty of Management and Accounting, Islamic Azad University, Central Tehran Branch, Tehran, Iran
چکیده [English]

The purpose of this study is to identify the potential customers to address in direct marketing programs, which has been regarded as one of the most important issues for direct marketers. The most important matter is the customer’s data set, which is always highly imbalanced. In this study, by combining the random under-sampling and over-sampling of the majority and minority classes that have been used frequently in past studies, we have designed and developed a dynamic and effective algorithm to identify and predict potential customers by clustering customers and extracting more balanced samples. For this purpose, a travel agency database (of over 10,000 records) has been used. The results indicate that customer's raw data cannot make a reliable prediction. On the other hand, Re-sampling methods using customer clustering and combining of minority and majority classes according to the proposed algorithm dramatically increases the prediction power of the decision tree and can be used in different situations and markets. Finally, by combining the results of the extracted XML codes and "multiple" criterion in each step, we can identify and rank potential customers and target them in an efficient way.

کلیدواژه‌ها [English]

  • Prediction optimization
  • Class imbalance
  • Data mining
  • Neural network
  1. Basiri, Mehdi, "Application of Data Mining Technique in Customer Relationship Management", National Conference on E-Commerce, Ministry of Industry, Mine and Trade, Iranian E-Commerce Association, 2007, Volume 4.
  2. Hari, Sadegh, Mehdi Mahdavi, & Kaveh. (2015). "Designing a Model for Predicting Credit Rating of Bank Customers Using Multi-Criteria Hyper-Algorithm and Ant-Fuzzy-Colony Neural Network Algorithm (Case Study of Tehran Bank Post Branches)". Management Research in Iran, 19 (1), 91-116.
  3. Hosseini. Mir Hassan, the Durban. Behnam, trustee, Maryam. (1392). "Assessing the Role of Promotion Mix in Increasing Sales of Cosmetics". Journal of Business Management Research, 5 (9), 21-38.
  4. Rezaei Navaei, Samira, Kousha, Hamid Reza, "Application and Evaluation of Data Mining Techniques to Predict Customer Turnover in the Insurance Industry", International Journal of Industrial Engineering and Production Management, Volume (27), Number (4), Vol (1-2017), Pages (635-653).
  5. Qasim Nia Arab. N, Safa Qadiklaee. A. (1397). "Comparison of Performance of Classic and Artificial Intelligence Models in Predicting Bank Clients' Credit Status". Journal of Business Management Research, 10 (20), 51-69.
  6. Anthonissen, P. (2008). Crisis communication: Practical PR strategies for reputation management & company survival: Kogan Page Publishers.
  7. Baesens, B., Viaene, S., Van den Poel, D., Vanthienen, J., & Dedene, G. (2002). Bayesian neural network learning for repeat purchase modelling in direct marketing. European Journal of Operational Research, 138(1), 191-211.
  8. Barandelaa, R., Sanchezb, J., & Garcia, V. (2003). Strategies for learning in class imbalance problems.
  9. Berry, M. J., & Linoff, G. (1997). Data mining techniques: for marketing, sales, and customer support: John Wiley & Sons, Inc.
  10. Chawla, N. V. (2009). Data mining for imbalanced datasets: An overview Data mining and knowledge discovery handbook (pp. 875-886): Springer.
11. Chen, Z.-Y., Fan, Z.-P., & Sun, M. (2015). Behavior-aware user response modeling in social media: Learning from diverse heterogeneous data. European Journal of Operational Research, 241(2), 422-434.
12. Coenen, F., Swinnen, G., Vanhoof, K., & Wets, G. (2000). The improvement of response modeling: combining rule-induction and case-based reasoning. Expert Systems with Applications, 18(4), 307-313.
13. Ding, A. W., Li, S., & Chatterjee, P. (2015). Learning user real-time intent for optimal dynamic web page transformation. Information Systems Research, 26(2), 339-359.
14. Elsner, R., Krafft, M., & Huchzermeier, A. (2004). Optimizing Rhenania's direct marketing business through dynamic multilevel modeling (DMLM) in a multicatalog-brand environment. Marketing Science, 192-206.
  1. Galar, M., Fernandez, A., Barrenechea, E., Bustince, H., & Herrera, F. (2012). A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 42(4), 463-484.
  2. Gönül, F. F., & Hofstede, F. T. (2006). How to compute optimal catalog mailing decisions. Marketing Science, 25(1), 65-74.
  3. Kara, A., & Kaynak, E. (1997). Markets of a single customer: exploiting conceptual developments in market segmentation. European journal of marketing, 31(11/12), 873-895.
  4. Knott, A., Hayes, A., & Neslin, S. A. (2002). Next product to buy models for cross selling applications. Journal of interactive Marketing, 16(3), 59-75.
  5. Kubat, M., Holte, R., & Matwin, S. (1997). Learning when negative examples abound. Paper presented at the European Conference on Machine Learning.
  6. Kubat, M., & Matwin, S. (1997). Addressing the curse of imbalanced training sets: one-sided selection. Paper presented at the Icml.
  7. Li, D.-C., Liu, C.-W., & Hu, S. C. (2010). A learning method for the class imbalance problem with medical data sets. Computers in biology and medicine, 40(5), 509-518.
  8. Napierała, K., Stefanowski, J., & Wilk, S. (2010). Learning from imbalanced data in presence of noisy and borderline examples. Paper presented at the International Conference on Rough Sets and Current Trends in Computing.
  9. Sun, B., Li, S., & Zhou, C. (2006). “Adaptive” learning and “proactive” customer relationship management. Journal of Interactive Marketing, 20(3-4), 82-96.
  10. Sun, Y., Wong, A. K., & Kamel, M. S. (2009). Classification of imbalanced data: A review. International Journal of Pattern Recognition and Artificial Intelligence, 23(04), 687-719.
  11. Uncles, M. D., Dowling, G. R., & Hammond, K. (2003). Customer loyalty and customer loyalty programs. Journal of consumer marketing, 20(4), 294-316.
  12. Yan, R., Liu, Y., Jin, R., & Hauptmann, A. (2003). On predicting rare classes with SVM ensembles in scene classification. Paper presented at the Acoustics, Speech, and Signal Processing, 2003. Proceedings.(ICASSP'03). 2003 IEEE International Conference on.
  13. Yang, Q., & Wu, X. (2006). 10 challenging problems in data mining research. International Journal of Information Technology & Decision Making, 5(04), 597-604.
  14. Zhang, J., & Krishnamurthi, L. (2004). Customizing promotions in online stores. Marketing Science, 23(4), 561-578.
  15. Zhang, S., Liu, L., Zhu, X., & Zhang, C. (2008). A strategy for attributes selection in cost-sensitive decision trees induction. Paper presented at the Computer and Information Technology Workshops, 2008. CIT Workshops 2008. IEEE 8th International Conference on.
  16. Armstrong, G., Adam, S., Denize, S., & Kotler, P. (2014). Principles of marketing: Pearson Australia.
  17. Jiang, P., & Rosenbloom, B. (2005). Customer intention to return online: price perception, attribute-level performance, and satisfaction unfolding over time. European journal of marketing, 39(1/2), 150-174.
  18. Achrol, R. S., & Kotler, P. (1999). Marketing in the network economy. The Journal of Marketing, 146-163.
  19. Hill, S., Provost, F., & Volinsky, C. (2006). Network-based marketing: Identifying likely adopters via consumer networks. Statistical Science, 21(2), 256-276.
  20. Lai, Y.-T., Wang, K., Ling, D., Shi, H., & Zhang, J. (2006). Direct marketing when there are voluntary buyers. Paper presented at the Data Mining, 2006. ICDM'06. Sixth International Conference on.
  21. Ling, C. X., & Li, C. (1998). Data mining for direct marketing: Problems and solutions. Paper presented at the Kdd.
  22. Kara, A., & Kaynak, E. (1997). Markets of a single customer: exploiting conceptual developments in market segmentation. European journal of marketing, 31(11/12), 873-895.
  23. Goebel, M., & Gruenwald, L. (1999). A survey of data mining and knowledge discovery software tools. ACM SIGKDD explorations newsletter, 1(1), 20-33.