The use of deep neural networks to make high risk decisions creates a need
for global and local explanations so that users and experts have confidence in
the modeling algorithms. We introduce a novel technique to
通过运用博弈论、局部特征交互作用效应和全局模型结构,我们实现了对基于树的机器学习模型的高可解释性,应用于三个医疗机器学习问题,在透露模型全局结构的同时保持其基本特征,识别出美国人口中高强度但低频率的非线性死亡风险因素,突显具有共同危险特征的明显人口亚组,识别出慢性肾脏疾病危险因素之间的非线性交互作用效应,并监测在医院部署的机器学习模型(Identifying factors leading to model's performance decay over time)