Customer Churn Prediction System Based on Flask
DOI:
https://doi.org/10.62051/bg4yj973Keywords:
Customer Churn Prediction; Machine Learning; Flask; Stacking Ensemble Model.Abstract
The article designs and implements a customer churn prediction system based on Flask, aimed at helping businesses identify potential customer churn risks through machine learning techniques. The system first loads and processes the input customer data, then utilizes various classifiers (such as Random Forest, Support Vector Machine, and XGBoost) to predict churn probabilities and provide corresponding customer retention suggestions. Methodologically, this study employs grid search for hyperparameter optimization to help the models achieve optimal performance. Additionally, a stacking approach is used to integrate the top-performing models from earlier stages, further enhancing predictive accuracy. Experimental results show that the ensemble method yields the best overall performance, achieving a prediction accuracy of 87%. In the future, the system can be expanded to include multi-source data fusion, real-time predictions, and the integration of feedback mechanisms, thereby realizing intelligent and personalized customer relationship management, providing new insights and technical support for customer retention in businesses.
Downloads
References
[1] Shaaban E, Helmy Y, Khedr A, et al. A proposed churn prediction model. International Journal of Engineering Research and Applications, 2012, 2(4): 693–697.
[2] Chang V, Hall K, Xu Q A, et al. Prediction of customer churn behavior in the telecommunication industry using machine learning models. Algorithms, 2024, 17(6): 231.
[3] Agarwal V, Taware S, Yadav S A, et al. Customer - churn prediction using machine learning. In: 2022 2nd International Conference on Technological Advancements in Computational Sciences (ICTACS), Tashkent, Uzbekistan. IEEE, 2022: 893–899.
[4] Jung S, Pramanik S. An efficient path computation model for hierarchically structured topographical road maps. IEEE Transactions on Knowledge and Data Engineering, 2002, 14(5): 1029–1046.
[5] Wu W W. Choosing knowledge management strategies by using a combined ANP and DEMATEL approach. Expert Systems with Applications, 2008, 35(3): 828–835.
[6] Sun Y, Yuan N J, Wang Y, et al. Contextual intent tracking for personal assistants. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016: 273–282.
[7] Rudd N A, Tetteh D N A, Boateng R. A multimodal fusion learning model for predicting customer churn risk in financial services. arXiv preprint, arXiv:2312.01301, 2023.
[8] Varshneya S, Ledent A, Liznerski P, et al. Interpretable tensor fusion. arXiv preprint, arXiv:2405.04671, 2024.
[9] Improved decision tree, random forest, and XGBoost algorithms for customer churn prediction. The Science and Information Organization, 2021. Available: https://thesai.org/Downloads/ Volume15No12/ Paper_68-Improved_Decision_Tree_Random_Forest_and_XGBoost_Algorithms.pdf
[10] Gayathri. Predicting customer churn using XGBoost: A comprehensive guide. Medium, 2023. Available: https://medium.com/@gayathri.s.de/predicting-customer-churn-using-xgboost-a-comprehensive-guide-d2d45d412f3b
[11] Building churn predictor with Python, Flask, HTML and CSS. Medium, 2021. Available: https://medium.com/star-gazers/building-churn-predictor-with-python-flask-html-and-css-fbab760e8441
Downloads
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2025 Transactions on Computer Science and Intelligent Systems Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
