Enhancing Digital Ad Personalization with AI: A Comparative Study of Collaborative Filtering, Content-Based Filtering, and Deep Learning Algorithms

Abstract

This study explores the efficacy of advanced artificial intelligence techniques in enhancing digital advertisement personalization by comparing collaborative filtering, content-based filtering, and deep learning algorithms. As online advertising continues to evolve, personalization has emerged as a critical component for improving user engagement and increasing conversion rates. The research employs a comprehensive dataset from a leading e-commerce platform encompassing user demographics, historical behavior, and feedback to evaluate each algorithm's performance. Collaborative filtering is assessed for its capability to leverage user similarity and collective preferences, while content-based filtering is analyzed for its use of item attributes in recommendation generation. The study further delves into deep learning approaches, particularly neural networks, to assess their ability to uncover complex, non-linear relationships within the data. Key performance indicators such as precision, recall, and F1-score are utilized to quantify each method's effectiveness. Results demonstrate that while collaborative and content-based filtering exhibit robust performance in user preference prediction, deep learning models outperform both by capturing intricate patterns and providing superior personalized recommendations. The paper concludes by discussing the implications of these findings for digital marketers, emphasizing the potential of deep learning to transform the landscape of targeted advertising by offering highly tailored ad experiences, ultimately driving greater customer satisfaction and business outcomes.