Balancing Privacy and Utility: Anonymisation Techniques for E-commerce Logistics Data

Abstract

The study analyses the application of anonymisation techniques in e-commerce logistics, focusing on methods such as differential privacy, k-anonymity, and synthetic data generation. The growing concerns over data privacy have prompted organisations in the matter of adopting techniques to protect the sensitive information of customers while maintaining data utility for analytical purposes. The case studies highlight real-world applications, like the use of differential privacy to enhance delivery route optimisation, synthetic data to improve inventory forecasting, and k-anonymity for protecting customer data during analysis. Despite the advancements in the techniques, the literature explores persistent challenges in preserving geospatial and temporal data utility, especially in dynamic environments like e-commerce logistics. The paper offers a comparative analysis of the latest research, by identifying gaps in the current literature and suggesting areas for further exploration, especially in the development of frameworks that are adaptive anonymisation and addressing risks of re-identification in large-scale datasets.