A Comparison of Machine Learning Classifiers for Evaluation of Remarketing Audiences in E-Commerce

Abstract

In this study, user data of an e-commerce site operating in Turkey is examined. Users are those who have visited the site before, that is, they are in the remarketing audience pool. The main goal is to make accurate predictions for remarketing and thus offer customized ad packages for new visitors. Visitors are labeled as "Shoppers" and "Non-shoppers" based on their previous visits. The data set is divided into two portions that do not intersect with each other as training and test sets. Three classification models based on artificial neural networks, classification and regression trees (CART), and random forest are built to make predictions and then classification performances of these models are compared.

Keywords

• Remarketing
• Google Analytics
• Artificial Neural Network
• Bagging
• Classification and Regression Tree(CART)
• Random Forest

E-Ticarette Yeniden Pazarlama Kitlelerinin Değerlendirilmesi için Makine Öğrenmesi Sınıflandırıcılarının Karşılaştırması

Abstract

Bu çalışmada, Türkiye'de faaliyet gösteren bir e-ticaret sitesinin kullanıcı verileri incelenmiştir. Bu kullanıcılar siteyi daha önce ziyaret eden, yani yeniden pazarlama (remarketing) kitle havuzu içerisinde bulunan kullanıcılardır. Temel amaç, yeniden pazarlama için doğru tahminler yapmak ve böylece yeni ziyaretçiler için özelleştirilmiş reklam içerikleri sunmaktır. Ziyaretçiler, e-ticaret sitesindeki önceki ziyaretlerine göre "alışveriş yapan" ve "alışveriş yapmayan" olarak etiketlendirilmiştir. Veri seti, eğitim ve test kümeleri olarak birbiriyle kesişmeyen iki bölüme ayrılmıştır. Tahmin yapmak için Yapay sinir ağlarına, sınıflandırma ve regresyon ağaçlarına (CART) ve rassal ormana (random forest) dayalı üç sınıflandırma modeli oluşturulmuş ve sınıflandırma performansları karşılaştırılmıştır.

Keywords

• Yeniden pazarlama
• Google Analytics
• Yapay Sinir Ağları
• Sınıflandırma ve Regresyon Ağaçları
• Torbalama
• Rassal Orman

References

1. Afrina, Y., Tasneem, S., & Fatema, K. (2015). Effectiveness of Digital Marketing in the Challenging Age: An Empirical Study. International Journal of Management Science and Business Administration, 1(5), 69-80.
2. Arrigo, E., Liberati , C., & Mariani, P. (2021). Social Media Data and Users' Preferences: A Statistical Analysis to Support Marketing Communication. Big Data Research, 24, 100189.
3. Ballestar, M., Grau, P., & Sainz, J. (2017). Customer segmentation in e-commerce: Applications to the cashback business model. Journal of Business Research, 88, 407-414.
4. Breiman, L. (1996). Bagging Predictors. Machine Learning(24), 123-140. Retrieved from https://doi.org/10.1023/A:1018054314350
5. Breiman, Leo, Jerome H. Friedman, Richard A. Olshen, and Charles J. Stone, Classification And Regression Trees, Chapman & Hall/CRC Texts in Statistical Science Series, 1984, İ
6. Charlesworth, A. (2018). Digital Marketing A Practical Approach (3rd edition ed.). New York: Routledge.
7. Ciaburro, G., & Venkateswaran, B. (2017). Neural Networks with R. Birmingham-Mumbai.: Packt Publishing.
8. Derevitskii, I., Severiukhina, O., & Bochenina, K. (2019). Clustering Interest Graphs for Customer Segmentation Problems. 2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS), (pp. 321-327).

9. Devi, G., & Das, D. (2020). Role of Customer segmentation in eMarketing. Solid State Technology, 63(5), 6251-6256.
10. Dogan, O., Hiziroglu, A., & Seymen, O. (2020). Segmentation of Retail Consumers with Soft Clustering Approach. Intelligent and Fuzzy Techniques: Smart and Innovative Solutions (pp. 39-46). Springer International Publishing.
11. Gupta, R., & Pathak, C. (2014). A Machine Learning Framework for Predicting Purchase by Online Customers based on Dynamic Pricing. Procedia Computer Science, 36, 599-605.
12. Haykin, S. (2008). Neural Networks and Learning Machines. New Jersey: Pearson Prentice Hall. doi:978-0131471399
13. Jäger, G. (2019). Replacing Rules by Neural Networks A Framework for Agent-Based Modelling. Big Data and Cognitive Computing, 3(4), 51. doi:10.3390/bdcc3040051
14. James, G., Witen, D., Hastie, T., & Tibshirani, R. (2014). An Introduction to Statistical Learning with Applications in R. New York: Springer. doi:10.1007/978-1-4614-7138-7
15. Lee, S. S. (2000). Noisy Replication in Skewed Binary Classification. Computational Statistics and Data Analysis, 2(34), 161-195. Retrieved from https://doi.org/10.1016/S0167-9473(99)00095-X
16. Levin, N., & Zahavi, J. (2001). Predictive modeling using segmentation. Journal of Interactive Marketing, 15, 2-22.
17. Liaw, A., & Wiener, M. (2002). Classification and Regression by randomForest. R News(2), 18-22. Retrieved from https://CRAN.R-project.org/doc/Rnews
18. Mitchell, T. M. (1980). The Need for Biases in Learning Generalizations. Rutgers University, Department of Computer Science.
19. Niu , X., Li, C., & Yu, X. (2017). Predictive Analytics of E-Commerce Search Behavior for Conversion. In AMCIS.
20. Öztemel, E. (2006). Yapay Sinir Ağları. İstanbul: Papatya Yayıncılık.
21. Patrutiu-Baltes, L. (2016). Inbound Marketing - the most important digital marketing strategy. Bulletin of the Transilvania University of Braşov Series V: Economic Sciences, 9 (58), 61-38.
22. Rokach, L. (2010). Pattern Classıfıcatıon Using Ensemble Methods (Serıes In Machine Perceptıon And Artificial Intelligence-Vol. 75). Singapore: World Scientific Publishing Company.
23. Rokach, L., & Maimon, O. (2015). Data Mining With Decision Tree Theory and Applications (2. ed.). World Scientific Publishing.
24. Safa, N., Ghani, N., & M. A., I. (2014). An artificial neural network classification approach for improving accuracy of customer identification in e-commerce. Malaysian Journal of Computer Science, 27(3), 171-185.
25. Silva, I., Spatti, D., Flauzino, R., Liboni, L., & Alves, S. (2017). Artificial Neural Networks: A Practical Course. Switzerland: Springer International Publishing. doi:10.1145/242224.242229
26. Therneau , T., & Atkinson, B. (2019). rpart: Recursive Partitioning and Regression Trees. Retrieved from https://CRAN.R-project.org/doc/Rnews/
27. Venables, W., & Ripley, B. (2002). Modern Applied Statistics with S (Fourth ed.). New York: Springer.
28. Wolpert, D., & Macready, W. (1995). No free lunch theorems for search. Technical Report SFI-TR-95-02-010(10).
29. Zhu, G., & Gao, X. (2019). Precision Retail Marketing Strategy Based on Digital Marketing Model. International Journal of Business and Management, 7, 33-37.
30. Online Resources https://ads.google.com/intl/tr_tr/home/how-it-works/, access date, 20.01.2020.
31. https://support.google.com/google-ads/answer/1722047, access date , 20.01.2020.
32. https://support.google.com/googleads/answer/117120?hl=tr, access date, 20.01.2020.
33. https://www.dijiseo.com/google-adwords-remarketing-yeniden-pazarlama-nasil-yapilir/, access data, 20.01.2020