Enhancing Clustering Stability, Compactness, and Separation in Multimodal Data Environments

Effective customer segmentation, crucial for tailored marketing strategies, relies on stable and distinct clustering methods. Traditional clustering approaches often focus on structured data, limiting their effectiveness when handling multimodal information. This study originally introduces a multimodal framework to enhance clustering stability, compactness, and separation by integrating categorical, numerical, and textual data. Our framework addresses existing limitations through three core components: a transformer-based embedding model for textual analysis, a data fusion layer for integrating diverse data types, and a generative model for refining cluster consistency. We rigorously assess the effectiveness of our framework using five stability metrics: Adjusted Rand Index (ARI), Adjusted Mutual Information Score (AMIS), BagClust (BG), Hierarchical Agglomerative Nesting (HAN), and Optimal Transport Alignment (OTA). Additionally, we use the Davies–Bouldin Score (DBS) to evaluate cluster compactness and separation. Real-world datasets (Yelp, Melbourne Airbnb, PetFinder.my, Women’s Clothing Reviews) were used to benchmark our approach against four existing methods. Results demonstrate that our framework achieves superior clustering stability, compactness, and separation, advancing multimodal learning for more nuanced customer segmentation.

Data & Knowledge Engineering (DKE)