This study delves into the dynamics of housing prices in Visakhapatnam, employing a multifaceted approach that combines linear regression modelling, geocoding, and K-means clustering. Leveraging a comprehensive dataset encompassing diverse locations, area (in square feet), and bedroom-bathroom configurations, we construct a robust linear regression model for price estimation. The dataset is further enriched through geocoding, introducing latitude and longitude coordinates to each location. Expanding our analysis, we employ K-means clustering to unveil spatial patterns and groupings within the housing market. Our findings reveal intricate relationships between location, property attributes, and housing prices, providing valuable insights for both prospective buyers and real estate stakeholders.Visualizations on the Visakhapatnam map illustrate the spatial distribution of housing clusters, shedding light on localized market trends. This integrated approach not only refines price predictions but also enhances our understanding of the spatial dynamics shaping the real estate landscape in Visakhapatnam. The outcomes of this study contribute to informed decision-making in the housing market and set the stage for future research exploring the nuances of regional real estate dynamics.