Understanding and Addressing Contractor Churn in the Thai Building Material Industry
คำสำคัญ:
Customer Churn, Building Material Industry, Causal Analysis, Prediction Modelingบทคัดย่อ
The Thai building materials market is vital for the country's growth, but suppliers often struggle with customer churn due to fluctuating prices, evolving standards, and changing customer preferences. In our study, we employed various machine learning models and determined that the XGBoost model demonstrated the highest accuracy in identifying potential contractor churns. Additionally, the model allows for the extraction of critical factors contributing to churn, enabling more customized and effective business interventions. Our results uncovered that while large orders can lead to higher churn, a concern since losing such high-value contracts can have a disproportionately large impact on revenue, regular purchases and active participation in loyalty programs significantly reduce it. To act on these insights, we recommend suppliers focus on building long-term relationships through tailored loyalty programs, exclusive offers, and localized engagement strategies. These practical suggestions, derived from our research, can boost profitability in this competitive market. Future work can adapt our methods to different industries, enhancing our understanding of churn and customer loyalty in diverse markets.
References
Ascarza, E., Neslin, S. A., Netzer, O., Anderson, Z., Fader, P. S., Gupta, S., ... & Schrift, R. (2018). In pursuit of enhanced customer retention management: Review, key issues, and future directions. Customer Needs and Solutions, 5(1), 65-81.
Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785-794).
Cenggoro, T. W., Wirastari, R. A., Rudianto, E., Mohadi, M. I., Ratj, D., & Pardamean, B. (2021). Deep learning as a vector embedding model for customer churn. Procedia Computer Science, 179, 624-631.
Du, S., Lee, J., & Ghaffarizadeh, F. (2019, July). Improve User Retention with Causal Learning. In The 2019 ACM SIGKDD Workshop on Causal Discovery (pp. 34-49). PMLR.
Lemaître, G., Nogueira, F., & Aridas, C. K. (2017). Imbalanced-learn: A python toolbox to tackle the curse of imbalanced datasets in machine learning. The Journal of Machine Learning Research, 18(1), 559-563.
Mirkovic, M., Lolic, T., Stefanovic, D., Anderla, A., & Gracanin, D. (2022). Customer Churn Prediction in B2B Non-Contractual Business Settings Using Invoice Data. Applied Sciences, 12(10), 5001.
Shah, M., Adiga, D., Bhat, S., & Vyeth, V. (2019). Prediction and causality analysis of churn using deep learning. Comput. Sci. Inf. Technol, 9(13), 153-165.
Sharma, A., & Kiciman, E. (2020). DoWhy: An end-to-end library for causal inference. arXiv preprint arXiv:2011.04216.
Wangperawong, A., Brun, C., Laudy, O., & Pavasuthipaisit, R. (2016). Churn analysis using deep convolutional neural networks and autoencoders. arXiv preprint arXiv:1604.05377.
Hason Rudd, D., Huo, H., & Xu, G. (2022). Improved Churn Causal Analysis Through Restrained High-Dimensional Feature Space Effects in Financial Institutions. Human-Centric Intelligent Systems, 2(3-4), 70-80.
