Improving the accuracy and relevance of suggestions for restaurants in the quickly changing field of recommendation systems is a major problem. Context-aware content considers context factors including time, location, and human context, while collaborative filtering considers user preferences and behaviors. To improve the precision of dining suggestions, Hybrid Content Boosted Collaborative filtering and Density-based spatial clustering approach (HCBCF_DBSCAN) integrates context-aware content with collaborative filtering approaches is proposed. The study offers a cutting-edge method for creating a customized and flexible restaurant recommendation system by fusing content based collaborative filtering with context-aware information. To generate scalable recommendations DBSCAN clustering is employed to find dense regions of restaurants in the feature space, which further improves recommendation accuracy. By putting comparable restaurants together, this clustering strategy helps to provide a variety of ideas that are still pertinent. Additionally, a user-user model is built to capture relationships and similarities between users, allowing the system to make recommendations based on shared characteristics with other users as well as past interactions. The effectiveness of the suggested system is assessed by means of a comparative study with conventional collaborative filtering approaches, employing measures like user happiness, variety, and accuracy.