Evaluating Factor Contributions for Sold Homes

We evaluate the contributions of ten intrinsic and extrinsic factors, including ESG (environmental, social, and governance) factors readily available from website data to individual home sale prices using a P-spline generalized additive model (GAM). We identify the relative significance of each factor by evaluating the change in adjusted R^2 value resulting from its removal from the model. We combine this with information from correlation matrices to identify the added predictive value of a factor. Based on data from 2022 through 2024 for three major U.S. cities, the GAM consistently achieved higher adjusted R^2 values across all cities (compared to a benchmark generalized linear model) and identified all factors as statistically significant at the 0.5% level. The tests revealed that living area and location (latitude, longitude) were the most significant factors; each independently adds predictive value. The ESG-related factors exhibited limited significance; two of them each adding independent predictive value. The elderly/disabled accessibility factor was much more significant in one retirement-oriented city. In all cities, the accessibility factor showed moderate correlation with one intrinsic factor. Despite the granularity of the ESG data, this study also represents a pivotal step toward integrating sustainability-related factors into predictive models for real estate valuation.