User segmentation under blockchain-based privacy protection

User segmentation is a marketing strategy that allows companies to more accurately position their products and services, thereby enhancing marketing efficiency and customer satisfaction. However, existing user segmentation approaches continue to face significant challenges related to personal information leakage and data security. To address these issues, this study proposes a data storage architecture that integrates localized differential privacy mechanisms with blockchain technology to ensure user data security and reduce the risk of privacy breaches. Building on this foundation, a clustering algorithm based on a density distance metric, referred to as the KDE-KMeans algorithm, is designed and implemented. In this algorithm, a density distance score is introduced as the core metric for measuring the similarity between samples and cluster centers. This scoring mechanism comprehensively considers the traditional distance as the primary factor in similarity evaluation, while also incorporating the density difference between samples as a secondary factor. Together, these elements form a more detailed and robust similarity evaluation framework.Experimental results demonstrate that the KDE-KMeans algorithm significantly outperforms baseline algorithms in clustering accuracy. Its advantages are especially pronounced when processing datasets with substantial density variations between clusters, highlighting the algorithm’s effectiveness and adaptability in complex data environments. • A blockchain-based secure storage mechanism that integrates differential privacy— specifically localized differential privacy (LDP)—is proposed. User data, perturbed via LDP to introduce controlled noise, is added to the blockchain only after reaching consensus through a multi-layered Practical Byzantine Fault Tolerance (PBFT) algorithm. This approach strikes an effective balance between user data security and privacy protection. • In this work, a density-distance-based clustering algorithm is proposed. This algorithm employs a density-distance score to measure the similarity between samples and cluster centers, facilitating adaptation to a broader range of user groups and thereby enhancing clustering accuracy. • By integrating the blockchain-based secure storage mechanism, differential privacy, and the KDE-KMeans clustering algorithm for user segmentation, companies can more precisely target their products and services, thereby enhancing marketing efficiency and customer satisfaction.