Integrating Machine Learning, SHAP Interpretability, and Deep Learning Approaches in the Study of Environmental and Economic Factors: A Case Study of Residential Segregation in Las Vegas DOI Creative Commons
Jiangran Liu, Yuxuan Cai, Xiwei Shen

и другие.

Land, Год журнала: 2025, Номер 14(5), С. 957 - 957

Опубликована: Апрель 29, 2025

Over the past two decades, research on residential segregation and environmental justice has evolved from spatial assimilation models to include class theory social stratification. This study leverages recent advances in machine learning examine how environmental, economic, demographic factors contribute ethnic segregation, using Las Vegas as a case with broader urban relevance. By integrating traditional econometric techniques deep models, investigates (1) correlation between housing prices, quality, segregation; (2) differentiated impacts various groups; (3) comparative effectiveness of predictive models. Among tested algorithms, LGBM (Light Gradient Boosting) delivered highest accuracy robustness. To improve model transparency, SHAP (SHapley Additive exPlanations) method was employed, identifying key variables influencing outcomes. interpretability framework helps clarify variable importance interaction effects. The findings reveal that prices poor quality disproportionately affect minority populations, distinct patterns across different groups, which may reinforce these groups’ economic marginalization. These effects persistent inequalities manifest themselves racial unequal burdens. methodology this is generalizable, offering reproducible for future studies other cities informing equitable planning policy.

Язык: Английский

Integrating Machine Learning, SHAP Interpretability, and Deep Learning Approaches in the Study of Environmental and Economic Factors: A Case Study of Residential Segregation in Las Vegas DOI Creative Commons
Jiangran Liu, Yuxuan Cai, Xiwei Shen

и другие.

Land, Год журнала: 2025, Номер 14(5), С. 957 - 957

Опубликована: Апрель 29, 2025

Over the past two decades, research on residential segregation and environmental justice has evolved from spatial assimilation models to include class theory social stratification. This study leverages recent advances in machine learning examine how environmental, economic, demographic factors contribute ethnic segregation, using Las Vegas as a case with broader urban relevance. By integrating traditional econometric techniques deep models, investigates (1) correlation between housing prices, quality, segregation; (2) differentiated impacts various groups; (3) comparative effectiveness of predictive models. Among tested algorithms, LGBM (Light Gradient Boosting) delivered highest accuracy robustness. To improve model transparency, SHAP (SHapley Additive exPlanations) method was employed, identifying key variables influencing outcomes. interpretability framework helps clarify variable importance interaction effects. The findings reveal that prices poor quality disproportionately affect minority populations, distinct patterns across different groups, which may reinforce these groups’ economic marginalization. These effects persistent inequalities manifest themselves racial unequal burdens. methodology this is generalizable, offering reproducible for future studies other cities informing equitable planning policy.

Язык: Английский

Процитировано

0