This paper introduces GeoShapley, a game theory approach to measuring spatial effects in machine learning models. GeoShapley extends the Nobel Prize-winning Shapley value framework in game theory by conceptualizing location as a player in a model prediction game, which enables the quantification of the importance of location and the synergies between location and other features in a model. GeoShapley is a model-agnostic approach and can be applied to statistical or black-box machine learning models in various structures. The interpretation of GeoShapley is directly linked with spatially varying coefficient models for explaining spatial effects and additive models for explaining non-spatial effects. Using simulated data, GeoShapley values are validated against known data-generating processes and are used for cross-comparison of seven statistical and machine learning models. An empirical example of house price modeling is used to illustrate GeoShapley's utility and interpretation with real world data. The method is available as an open-source Python package named geoshapley.

该论文介绍了GeoShapley，一种衡量机器学习模型中空间效应的博弈论方法。GeoShapley扩展了诺贝尔奖获奖的Shapley值框架，将位置作为模型预测博弈中的参与方，可以量化位置的重要性以及位置与其他特征之间的协同作用。GeoShapley是一种与模型无关的方法，可应用于具有不同结构的统计学或黑盒机器学习模型，并与解释空间效应的空间变异系数模型以及解释非空间效应的加法模型直接相关联。通过模拟数据验证了GeoShapley值以及用于七个统计学和机器学习模型的交叉比较。使用房价建模的实证例子说明了GeoShapley的实用性和解释性。该方法可作为一个名为geoshapley的开源Python包使用。

GeoShapley：一种测量机器学习模型中空间效应的博弈论方法