MACHINE LEARNING-BASED OPTIMIZATION OF DIGITAL AD PLACEMENT: A LITERATURE REVIEW
Keywords:
Digital Advertising, Ad Placement, Machine Learning, Collaborative Filtering, Reinforcement Learning, Clustering, Click-Through Rate.Abstract
The exponential growth of digital advertising across online platforms has intensified the need for effective ad placement strategies aimed at maximizing user engagement. Traditional ad placement methods, relying on heuristic rules and demographic targeting, have shown limitations in their ability to adapt to dynamic user behaviors. This paper reviews existing research on machine learning-based approaches to optimize ad placement, focusing on three main techniques: collaborative filtering, reinforcement learning, and clustering. We conduct a comparative analysis of these techniques concerning engagement metrics such as click-through rates (CTR), user retention, and time spent on ads. Results from reviewed studies indicate that machine learning-based models significantly outperform traditional methods, with improvements in personalization, adaptability, and segmentation. This review underscores the potential of integrating machine learning to enhance digital ad placements, offering substantial gains in user interaction and engagement.
