In Community detection is a fundamental technique in network analysis that makes it possible to identify strongly connected groups within a network. In real-world applications like social networks, e-commerce platforms, recommendation systems, and financial transactions, communities offer valuable insights into user behavior, product relationships, and transactional patterns. Although there is an increasing need for efficient community detection, current approaches like label propagation, spectral clustering, and modularity-based approaches have a number of drawbacks. In order to overcome these constraints, the Enhanced Adaptive Graph-Based Community Detection (EAGBCD) technique is proposed, which improves community detection by utilizing edge-weighted clustering, adaptive modularity optimization, and graph-based learning. The proposed method improves modularity, computational efficiency, and clustering accuracy by dynamically adapting to changing network structures, in contrast to traditional methods. The novelty of proposed method lies in its ability to adapt dynamically to evolving, multi-layered networks and detect overlapping as well as hierarchical communities, overcoming the resolution limits and scalability challenges of prior approaches. Experimental results on the Online Retail dataset show that EAGBCD achieved the highest modularity score (0.62) compared to Louvain (0.51) and Label Propagation (0.48), while reducing execution time by nearly 40%. It also produced denser and more cohesive communities with higher clustering coefficients, and improved targeted advertising by increasing Click-Through Rates up to 0.28, significantly outperforming baseline methods. These findings demonstrate that proposed framework provides a scalable, accurate, and efficient solution for community detection with direct impact on applications such as personalized marketing, fraud detection, and recommendation systems. The proposed method is evaluated on real-world datasets, including the widely used Online Retail dataset, which captures customer purchase transactions and product co-occurrences.