DIFFERENTIAL PRIVACY-BASED PROTECTION OF USER SHOPPING PREFERENCES IN E-COMMERCE SYSTEMS

Abstract

This study investigates the potential of differentiated privacy to safeguard the purchase preferences of online consumers while simultaneously enabling data analysis and personalized services. Protecting user privacy is a challenging endeavor due to the extensive collection of customer data by online purchasing websites. This study examines the potential of differential privacy techniques to conceal customers' private purchasing habits by introducing controlled noise to data without affecting the accuracy of the analysis. It also maintains a balance between data privacy and service quality to guarantee that enterprises can acquire critical knowledge while safeguarding customer data. The results indicate that differential privacy is a dependable and efficient method for fostering user confidence, alleviating privacy concerns, and facilitating secure data exchange in contemporary e-commerce.