Collaborative Advertisement Recommendation System Leveraging User Preferences, Geography, and Demographics

The increasing demand for personalized advertising based on user preferences is driving a surge in popularity. Social networks utilize millions of user’ data to suggest ads based on specific criteria. However, many of these ads can be uninteresting. This paper presents a collaborative advertisement recommendation system that leverages users’ preferences along with geographic and demographic data to deliver engaging ads. The system employs the K-dtree algorithm to efficiently organize users into interest-based communities and model complex patterns within those communities to enhance ad relevance. The dataset, collected via Hazmit provides a rich source of information. The system’s performance was evaluated based on precision, recall, F-score, and accuracy metrics, as well as running time measurements. The results highlighted the superior effectiveness of the K-dtree-based approach in accurately targeting the right customers for advertisements. Overall, the K-dtree method improves ad targeting accuracy, especially for food and demographics, but struggles with news due to subjectivity and regional biases.

• advertisement recommendation
• collaborative filtering
• personalized advertising
• user preferences
• geographic data
• demographic data
• communities of interest
• targeted advertising
• social networks

• Recommender Systems and Techniques
• Information Retrieval and Search Behavior
• Digital Marketing and Social Media
• advertisement recommendation
• collaborative filtering
• personalized advertising
• user preferences
• geographic data
• demographic data
• communities of interest
• targeted advertising
• Information Systems
• Sociology and Political Science
• Computer Science
• Social Sciences