Industrial Innovations

Industrial Innovations

Study on preventing e-commerce customer churn based on a business intelligence strategy based on machine learning (Case study: Pasargad Electronic Payment Company)

Document Type : Original Article

Authors
Reyhaneh Osati ahari 1
Elham Ramezani 2
1 Department of Business Administration, Faculty of Management, Islamic Azad University, Central Tehran Branch, Tehran, Iran
2 Department of Information Technology Management, Faculty of Management, Islamic Azad University, Central Tehran Branch, Tehran, Iran
10.61882/jii.2.3.264
Abstract
Customer churn is one of the fundamental and critical challenges in the e-commerce space that has a direct and widespread impact on the profitability, growth, and long-term sustainability of organizations. The main goal of this research is to provide a comprehensive and efficient model for predicting and preventing customer churn in the e-commerce context by utilizing modern business intelligence technologies and advanced machine learning algorithms. In this direction, the Support Vector Machine (SVM) algorithm was selected as a powerful tool for analyzing customer data and predicting their behavior. For this purpose, first, real and valid data was collected from customers of an active e-commerce platform. Then, data preprocessing steps including cleaning, normalization, and selection of influential features were carefully performed to optimize the quality of data for training the model. The SVM model was trained based on this processed data and then evaluated using standard evaluation criteria including Accuracy, Recall, and the F1 composite criterion. The results showed that the model has a good ability to identify customers at risk of churn with acceptable accuracy and can be used as an effective tool in predicting customer behavior. Next, in order to examine the managerial and organizational dimensions of the issue, hypotheses related to the factors affecting customer churn were developed and analyzed using valid statistical tests. The findings indicate that the business intelligence approach based on machine learning plays a prominent role not only in predicting churn but also in improving strategic decision-making processes and customer retention. This research, while promoting scientific knowledge in the field of customer churn management, provides practical and effective solutions to improve the organization's interactions with customers and increase their satisfaction and loyalty. Finally, the proposed model can help organizations to develop and implement targeted and efficient policies and strategies to reduce churn and strengthen customer loyalty by more accurately recognizing customer behavior patterns.
Keywords
Customer churn
E-commerce
Business intelligence
Machine learning ML
[1]    Al Rahib M. A, Saha N, Mia R, Sattar, A. Customer data prediction and analysis in e-commerce using machine learning. Bulletin of Electrical Engineering and Informatics. 2024;13(4), 2624-2633.
[2]    Anjaningrum W. D, Azizah N, Suryadi N. Spurring SMEs’ performance through business intelligence, organizational and network learning, customer value anticipation, and innovation-Empirical evidence of the creative economy sector in East Java, Indonesia. Heliyon. 2024;10(7).
[3]    Imani M, Joudaki, M, Beikmohamadi A, Arabnia H. R. Customer Churn Prediction: A Review of Recent Advances, Trends, and Challenges in Conventional Machine Learning and Deep Learning. 2025.
[4]    Manimaran P, Vignesh R, Vignesh B, Thilak, G. Enhanced Prediction of Lung Cancer Stages using SVM and Medical Imaging. Paper presented at the 2025 International Conference on Electronics and Renewable Systems (ICEARS). 2025.
[5]    Han X, Lin T X, Wang  X. Mitigate cross-market competition caused by the risk of uncertainty and improve firm performance through business intelligence. Heliyon. 2024;10(14).
[6]    Leonid T T, Jayaparvathy R. Classification of Elephant Sounds Using Parallel Convolutional Neural Network. intelligent automation & soft computing. 2022; 32(3).
[7]    Tang H Y. Ya’acob S. E-Commerce Customer Churn Prediction for the Marketplace in Malaysia. Open International Journal of Informatics. 2023;11(2):58-66.
[8]    Saxena M, Aggarwal N, Gupta R. Customer Churn Rate Prediction Using Machine Learning Techniques. Innovative Computing and Communications: Proceedings of ICICC. 2024: 3:1039, 365.
[9]    Matuszelański K., Kopczewska K. Customer churn in retail e-commerce business: Spatial and machine learning approach. Journal of Theoretical and Applied Electronic Commerce Research. 2022;17(1):165-198.
[10]    Urbancokova V, Kompan M, Trebulova Z, Bielikova, M. Behavior-based customer demography prediction in E-commerce. Journal of Electronic Commerce Research. 2020; 21(2): 96-112.
[11]    Amuda K. A, Adeyemo A. B. Customers churn prediction in financial institution using artificial neural network. 2019:1912.11346.
[12]    Nithya N, & Kiruthika R. Impact of Business Intelligence Adoption on performance of banks: a conceptual framework. Journal of Ambient Intelligence and Humanized Computing. 2021;12(2): 3139-3150.
[13]    Xiahou X, Harada, Y. (2022). B2C E-commerce customer churn prediction based on K-means and SVM. Journal of Theoretical and Applied Electronic Commerce Research. 2022; 17(2): 458-475.
[14]    Huang Z.-x, Savita K, Dan-yi L, Omar A. H. The impact of business intelligence on the marketing with emphasis on cooperative learning: Case-study on the insurance companies. Information Processing & Management. 2022; 59(2): 102824.
[15]    Doko F,  Miskovski I. An overview of big data analytics in banking: Approaches, challenges and issues. 2019.
[16]    Jothi T. N, Kumar A. S, Dutta A, Musirin I. B, Rao L. M, Vanishree G, Srinivasulu A. Customer Churn Prediction Using SVM for Finance Essential Information Systems Service Management.  2025:113-132: IGI Global.
[17]    Mohammad-Khan K, Behnaz, Rahimian A. The impact and role of business intelligence in the banking industry. 2024.
[18]    Sadeghi A, Tavakoli S, Omidi-Nasab M. Performance diagnosis of banks in implementing modern marketing and sales methods for services and products. Proceedings of the Conference on Information Technology, Georgia. 2022.
[19]    Tiwari P. P, Yuktha, G. P, Manimaran A. Utilizing Business Intelligence and Machine Learning in CRM Data to Reduce Customer Churn in E-commerce Platforms. In AI-Powered Business Intelligence for Modern Organizations. 2025: 207-242. IGI Global.
 
Industrial Innovations
Volume 2, Issue 3 - Serial Number 7
Summer 2024
Pages 264-284

  • Receive Date 24 July 2025
  • Revise Date 30 August 2025
  • Accept Date 06 September 2025