Toward Enhanced Privacy in Digital Marketing: An Integrated Approach to User Modeling Utilizing Deep Learning on a Data Monetization Platform

Abstract

This paper introduces an innovative method for safeguarding user privacy in digital marketing campaigns through the application of deep learning techniques on a data monetization platform. This framework empowers users to maintain authority over their personal data while enabling marketers to pinpoint suitable target audiences. The system consists of several key stages: initially, representation learning in hyperbolic space captures latent user interests across various data sources with hierarchical structures. Subsequently, Generative Adversarial Networks generate synthetic user interests from these embeddings. To preserve user privacy, Federated Learning is utilized for decentralized user modeling training, ensuring data remains undisclosed to marketers. Lastly, a targeting strategy, rooted in recommendation systems, utilizes learned user interests to identify optimal target audiences for digital marketing campaigns. In sum, this approach offers a comprehensive solution for privacy-preserving user modeling in digital marketing.