1# RECORD db3684d67741de25ae92064ef093bf9c1d604ef82# TITLE: Analyzing Key Determinants of Property Valuation in Boston Neighborhoods3# YEAR: 2025.0 VENUE: Advances in Economics, Management and Political Sciences DOI: 10.54254/2754-1169/2025.bj257524# AUTHORS: Shuo Xin5# PAGES: 9 CANDIDATE TABLE PAGES (1-based): [6]6# ABSTRACT: The current research examines the effects of particular attributes of dwellings on property valuation in neighborhoods of Boston. Given the increased sophistication of urban property markets, particularly in historically dense cities such as Boston, this study aims to offer data-based insights into factors most influential in property valuation. Employing the Boston 2024 property assessment data set from the Boston open data portal, this research utilizes multiple linear regression and K-means cluster analysis to conduct a broad investigation. Multiple linear regression measures the relationship between physical attributesland value, number of bathrooms, and living spaceand appraisal value. In contrast, K-means clustering identifies latent property groupings involving similarities in structure and market value level. Results demonstrate that area size, number of full bathrooms, and land value are the main contributing factors in higher values, while other factors, such as number of kitchens and some ZIP codes, negatively impact property value. These findings offer actionable information to homeowners, builders, and investment, urban design, and housing policy in Boston.789===== PAGE 1 (score 12, numeric-paren 0, table-words 0, var-words 12) =====1011Proceedings of ICEMGD 2025 Symposium: The 4th International Conference on Applied Economics and Policy Studies12DOI: 10.54254/2754-1169/2025.BJ2575213© 2025 The Authors. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.014(https://creativecommons.org/licenses/by/4.0/).1519616Analyzing Key Determinants of Property Valuation in Boston17Neighborhoods18Shuo Xin19D'Amore-McKim School of Business, Northeastern University, Boston, USA20shuoxin4@gmail.com21Abstract. The current research examines the effects of particular attributes of dwellings on22property valuation in neighborhoods of Boston. Given the increased sophistication of urban23property markets, particularly in historically dense cities such as Boston, this study aims to24offer data-based insights into factors most influential in property valuation. Employing the25Boston 2024 property assessment data set from the Boston open data portal, this research26utilizes multiple linear regression and K-means cluster analysis to conduct a broad27investigation. Multiple linear regression measures the relationship between physical28attributes—land value, number of bathrooms, and living space—and appraisal value. In29contrast, K-means clustering identifies latent property groupings involving similarities in30structure and market value level. Results demonstrate that area size, number of full31bathrooms, and land value are the main contributing factors in higher values, while other32factors, such as number of kitchens and some ZIP codes, negatively impact property value.33These findings offer actionable information to homeowners, builders, and investment, urban34design, and housing policy in Boston.35Keywords: Property Valuation, Linear Regression, K-means Clustering361. Introduction37American city real estate markets are volatile, with housing affordability and urban planning as key38issues. Boston's housing market is unique, with heterogeneous neighborhoods and fluctuating39property values [1]. In the context of expanding urban populations and real estate investment, it is40critical for stakeholders to understand the factors that influence property appraisal values [2].41Prior research has established the impact of urban amenities, public transit, and educational42infrastructure on property valuations. Prior research offers broad housing price insights, but neglects43Boston's micro-market dynamics. Existing models often lack interpretability and local feature44integration. This study aims to fill that gap by investigating how specific physical features of45properties—such as living area, number of bathrooms, year of remodeling, land value, and more—46correlate with and influence property appraisal values in different neighborhoods across Boston.47This study utilizes multiple linear regression and K-means clustering to analyze the relationship48between housing characteristics and property appraisal value. This study selects explicit regression49because the prediction target—appraisal value—is a continuous, numeric variable, making50regression analysis more appropriate than classification methods designed for categorical or515253===== PAGE 6 (score 14, numeric-paren 0, table-words 2, var-words 8) =====5455Proceedings of ICEMGD 2025 Symposium: The 4th International Conference on Applied Economics and Policy Studies56DOI: 10.54254/2754-1169/2025.BJ257525720158(RMSE) was roughly $279,830, which reflects the typical deviation of the model's predictions from59actual property values.602.5. K-means clustering analysis61K-means clustering is an unsupervised learning algorithm. It divides the data into K non-62overlapping clusters by calculating the distances between samples [6]. K-means clustering was63applied as an unsupervised learning technique to uncover hidden patterns in the property dataset64beyond supervised modeling. A diverse sample of 7,000 properties was used to reduce65computational load. The Elbow Method and Silhouette Scores were used to determine the optimal66number of clusters, with the Elbow plot indicating three clusters. The Silhouette analysis showed67relatively high scores for three clusters, suggesting that this choice would yield well-separated and68cohesive groupings.69Figure 5. Elbow method curve and silhouette score plot for K-means70Based on the clustering results:71• Cluster 0 predominantly included larger family homes with substantial gross-living areas and72moderate appraisal values.73• Cluster 1 consisted of smaller, lower-valued properties, often characterized by limited living space74and fewer amenities.75• Cluster 2 represented luxury homes with expansive living spaces, multiple bathrooms, and the76highest overall appraisal values.77Table 2. Mean feature values across K-means clusters78Clust79er80LIVING_A81REA82FULL_83BTH84LAND_VA85LUE86HLF_B87TH88BED_R89MS90KITCH91ENS92GROSS-93LIVING94LAND_95SF96OWN_OC97C_Y98TOTAL_V99ALUE10001012356.8336102771032.375711046105198065.57106851070.3762108891094.3087011061111.6666611271131005.1955311431153471.5761161741170.56071118124093611911201212.758012161221.395412357066.51012481250.1731262.3811271.1462128371.985341291909.30213021310.5344132591606.813321342787.5183135071362.744091374138354708.66139141400.7401141571423.8307014391441.330701459146517.245472 2948.0701478661480.6141731492929574150These clusters(Table 2) provide a valuable segmentation of the Boston real estate market,151complementing the regression findings and offering additional perspectives for understanding152153154===== PAGE 7 (score 19, numeric-paren 0, table-words 4, var-words 11) =====155156Proceedings of ICEMGD 2025 Symposium: The 4th International Conference on Applied Economics and Policy Studies157DOI: 10.54254/2754-1169/2025.BJ25752158202159property value dynamics across different neighborhoods.1603. Results and discussion1613.1. Correlation analysis results162Correlation Analysis is a statistical method used to quantify the strength and direction of the linear163relationship between two or more variables, and its results are usually expressed by the correlation164coefficient (between -1 and 1) [7]. The correlation analysis provided initial insights into the165relationships between various physical features of properties and their appraisal values. As shown in166Figure 1, the correlation heatmap revealed that the living area exhibited the strongest positive167relationship with property value among all features considered. The results align with real estate168market trends, where larger living areas correlate with higher prices. Full bathrooms and land value169also showed positive correlations, indicating their significant contribution to property valuation.170Conversely, specific features, such as the number of kitchens and the number of bedrooms,171showed weaker or even slightly negative correlations with property value. This result implies that172beyond a certain threshold, adding more kitchens or bedrooms may not linearly increase a property's173market value and may even indicate property types with lower per-unit value, such as multi-family174residences.175The bar plot of feature correlations presented in Figure 2 further ranked these relationships176quantitatively. Living area and full bathrooms emerged as dominant contributors, confirming their177importance for further modeling steps. Additionally, the boxplot in Figure 3 illustrates that owner-178occupied properties tend to have slightly higher median appraisal values than non-owner-occupied179properties. This observation suggests that owner occupancy could be a proxy for better property180maintenance and investment in amenities, ultimately enhancing market value.1813.2. Multiple linear regression model findings182The multiple linear regression model provided interpretable results, quantitatively linking property183characteristics to appraisal values [8]. Regression coefficients indicated that an additional square184foot of living area increased appraisal value by approximately $414, with additional full bathrooms185also contributing positively to valuation. Land value maintained a steady positive slope.186Interestingly, the number of kitchens had a negative coefficient, indicating that properties with187multiple kitchens, possibly multi-unit dwellings, tended to have lower appraisal values when188controlling for other factors. This outcome emphasizes that not all amenities uniformly increase189property worth.190A critical dimension uncovered through the regression analysis was the effect of ZIP codes on191property values. Figure 5 displays the ZIP code coefficient distribution, illustrating Boston's192significant geographic disparities. ZIP code 02108 (Beacon Hill) properties had the highest positive193adjustment of over $589,000, reflecting the area's historical prestige, central location, and194architectural significance. In contrast, ZIP code 02121 (Dorchester) was associated with a195substantial negative adjustment of approximately $432,000. This contrast highlights how location,196independent of structural features, is critical in determining real estate market dynamics in urban197environments.198The model achieved an R-squared value of 0.736, indicating a strong fit, with approximately 74%199of the variation in property appraisal values explained by the selected features. The Root Mean200Square Error (RMSE) of $279,830 is reasonable given Boston's overall high property price levels.201