Published Paper Details:

The rise of e-commerce has posed challenges for businesses regarding returns, cancellations and varied payment preferences while ensuring customer satisfaction. This paper proposes an innovative methodology that utilizes big data, Machine Learning Techniques and statistical analysis to construct customer profiles while upholding individual privacy. Through the aggregation and anonymization of customer data, the system generates personalized credit and purchasing profiles. This data-driven approach enables tailored delivery benefits and EMI options for customers. Notably, the system categorizes customers based on their credit and purchasing behavior, limiting Cash on Delivery for users with unfavorable buying profiles and withholding EMI choices for those with less favorable credit profiles. Prioritizing privacy protection, this solution optimizes e-commerce operations while respecting customer confidentiality, striking a balance between service customization and privacy preservation.