The Effect of Customer Behavior on Conversion Rates in Digital Marketing Campaigns: Data Analytics and Random Forest Model Approach

Öz

This study was conducted by analyzing the data of customers participating in a digital marketing campaign and examining the factors affecting conversion rates. As a result of the calculated Exploratory Data Analysis (EDA), it was determined that age, income, website interactions and advertising expenditure variables had significant effects on conversion. In the modeling phase, the Random Forest classification algorithm was used to estimate conversion rates. The overall accuracy score of the model was calculated as 88.12%. However, it was observed that the model was weak in predicting the “No Conversion” class, but on the contrary, it showed high performance in the “Conversion” class. This situation, which arises from the unbalanced data distribution, shows that class balance strategies can be used to improve the model. The results of the analysis show that advertising expenditures, website visits and click-through rates have significant effects on conversion. These findings emphasize that digital marketing strategies should be optimized with personalized approaches.

Anahtar Kelimeler

• Digital Marketing
• Customer Conversion
• Data Analytics
• Random Forest
• Campaign Performance

Dijital Pazarlama Kampanyalarında Müşteri Davranışlarının Dönüşüm Oranları Üzerindeki Etkisi: Veri Analitiği ve Random Forest Modeli Yaklaşımı

Öz

Bu çalışma, e ticaret siteleri aracılığı ile alışverişlerini gerçekleştiren ve bir dijital pazarlama kampanyasına katılan müşterilerin verilerinin analiz edilerek, dönüşüm (conversion) oranlarını etkileyen faktörlerin incelenmesi ile gerçekleştirilmişti. Hesaplanan Keşifsel Veri Analizi (EDA) sonucunda, yaş, gelir, web sitesi etkileşimleri ve reklam harcamaları değişkenlerinin, dönüşüm üzerinde önemli etkiler yarattığı tespit edilmiştir. Modelleme aşamasında, dönüşüm oranlarını tahmin etmek için Random Forest sınıflandırma algoritması kullanılmıştır. Modelin genel doğruluk skoru %88.12 olarak hesaplanmıştır. Ancak, modelin “Dönüşüm Yok” sınıfını tahmin etmede zayıf kaldığı, bunun aksine “Dönüşüm” sınıfında yüksek bir performans sergilediği görülmüştür. Dengesiz veri dağılımından kaynaklanan bu durum, modelin iyileştirilmesi için sınıf dengesi stratejilerinin kullanılabileceğini göstermektedir. Analiz sonuçları, reklam harcamaları, web sitesi ziyaretleri ve tıklama oranlarının dönüşüm üzerinde önemli etkileri olduğunu göstermektedir. Bu bulgular, dijital pazarlama stratejilerinin kişiselleştirilmiş yaklaşımlarla optimize edilmesi gerektiğini vurgulamaktadır.

Anahtar Kelimeler

• Dijital Pazarlama
• Müşteri Dönüşümü
• Veri Analitiği
• Random Forest
• Kampanya Performansı

Kaynakça

1. Alfajr, N. H., Defiyanti, S. (2024). Prediksi Penyakit Jantung Menggunakan Metode Random Forest Dan Penerapan Principal Component Analysis (PCA). Jurnal Informatika Dan Teknik Elektro Terapan, 12(3S1).
2. Amajuoyi, C. P., Nwobodo, L. K., Adegbola, A. E. (2024). Utilizing Predictive Analytics to Boost Customer Loyalty and Drive Business Expansion. GSC Advanced Research and Reviews, 19(3), 191–202.
3. Ayanso, A., Yoogalingam, R. (2009). Profiling Retail Web Site Functionalities and Conversion Rates: A Cluster Analysis. International Journal of Electronic Commerce, 14(1), 79-114.
4. Chaffey, D., & Smith, P. (2022). Digital Marketing Excellence. Routledge.
5. Cui, Y., Tobossi, R., Vigouroux, O. (2018). Modelling Customer Online Behaviours with Neural Networks: Applications to Conversion Prediction and Advertising Retargeting.
6. Çolak H., Kağnıcıoğlu C.H., Argan M., 2022, Sosyal Medyada Etkileşim ve Dönüşüm Orani Arasindaki İlişkinin İncelenmesine Yönelik Facebook Örneği, Elektronik Sosyal Bilimler Dergisi, 21(81).
7. Dai, Z., Hu, Z., Shen, T., & Zhang, Y. (2023). Risk Prediction of Diabetes Based on Spark and Random Forest Algorithm. 2023 IEEE 2nd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA), 535–539.
8. Doğanlı, B., Çelik, S. (2024). Pazarlama Stratejileri için Veri Bilimi ve Python (1st ed.). All Sciences Academy.

9. Guo, Y., Ao, X., Liu, Q., He, Q. (2023). Leveraging Post-Click User Behaviors for Calibrated Conversion Rate Prediction Under Delayed Feedback in Online Advertising. Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, 3918–3922.
10. Gürsakal, N., Çelik, S. (2021). Büyük Veri ve Pazarlama (Birinci Baskı). Dora Yayınevi.
11. Holzwarth, M., Janiszewski, C., Neumann, M. M. (2006). The Influence of Avatars on Online Consumer Shopping Behavior. Journal of Marketing, 70(4), 19-36.
12. Hong, S. (2024). Data-driven Precision Marketing Strategy and Its Effect Measurement. Transactions on Economics, Business and Management Research, 12, 59–64.
13. Ignatenko, V., Surkov, A., Koltcov, S. (2024). Random Forests with Parametric Entropy-Based Information Gains for Classification and Regression Problems. PeerJ Computer Science, 10, e1775.
14. Ijomah, T. I., Idemudia, C., Eyo-Udo, N. L., Anjorin, K. F. (2024). Harnessing Marketing Analytics for Enhanced Decision-Making and Performance in SMEs. World Journal of Advanced Science and Technology, 6(1), 001–012.
15. Kristiana, I., Prabowo, H., Gaol, F. L., & Qomariyah, N. N. (2024). Review of Critical Components of Data-Driven Nudge Theory on Enhancing Conversion Rates in Digital Marketing Campaigns. 2024 International Conference on Information Technology Research and Innovation (ICITRI), pp: 263–268.
16. Kumar, D., Kothiyal, A., Kumar, R., Hemantha, C., Maranan, R. (2024). Random Forest approach optimized by the Grid Search process for predicting the dropout students. 2024 International Conference on Innovations and Challenges in Emerging Technologies (ICICET), 1–6.
17. Liu, J., Zhou, X., Wei, Y., Lu, L. (2024). Research on Machine Learning and Financial Risk Early Warning of Listed Companies Based on Random Forest Model. Frontiers in Humanities and Social Sciences, 4(9), 226–229.
18. Mali, M., Mangaonkar, N. (2023). Behavioral Customer Segmentation for Subscription. 2023 3rd Asian Conference on Innovation in Technology (ASIANCON), 1–6.
19. McDowell, W. C., Wilson, R. C., Kile Jr, C. O. (2016). An Examination of Retail Website Design and Conversion Rate. Journal of Business Research, 69(11), 4837-4842.
20. Nwabekee, U. S., Abdul-Azeez, O. Y., Agu, E. E., & Ijomah, T. I. (2024). Digital Transformation in Marketing Strategies: The Role of Data Analytics and CRM Tools. International Journal of Frontline Research in Science and Technology, 3(2), 055–072.
21. Rogić, S., Kašćelan, L. (2023). Decoding Customer Behaviour: Relevance of Web and Purchasing Behaviour in Predictive Response Modeling, 369–380.
22. Salman, H. A., Kalakech, A., Steiti, A. (2024). Random Forest Algorithm Overview. Babylonian Journal of Machine Learning, 69–79.
23. Söderlund, M., Berg, H., Ringbo, J. (2014). When the Customer Has Left the Store: An Examination of The Potential for Satisfaction Rub-Off Effects and Purchase Versus No Purchase Implications. Journal of Retailing and Consumer Services, 21(4), 529-536.
24. Sun, C. (2024). Data Analysis of Customer Segmentation and Personalized Strategy in the Era of Big Data. Advances in Economics, Management and Political Sciences, 92(1), 46–52.
25. Talaat, F. M., Aljadani, A., Alharthi, B., Farsi, M. A., Badawy, M., Elhosseini, M. (2023). A Mathematical Model for Customer Segmentation Leveraging Deep Learning, Explainable AI, and RFM Analysis in Targeted Marketing. Mathematics, 11(18), 3930.
26. Yeo, J., Hwang, S.-W., Kim, S., Koh, E., Lipka, N. (2020). Conversion Prediction from Clickstream: Modeling Market Prediction and Customer Predictability. IEEE Transactions on Knowledge and Data Engineering, 32(2), 246–259.