Standard supervised learning procedures are validated against a test set that is assumed to have come from the same distribution as the training data. However, in many problems, the test data may have come from a different distribution. We consider the case of having many labeled observations from one distribution, P₁, and wanting to make predictions at unlabeled points that come from P₂. We combine the high predictive accuracy of random forests with an importance sampling scheme, where the splits and predictions of the base trees are done in a weighted manner, which we call locally optimized random forests. These weights correspond to a non‐parametric estimate of the likelihood ratio between the training and test distributions. To estimate these ratios with an unlabeled test set, we make the covariate shift assumption, where the differences in distribution are only a function of the training distributions. This methodology is motivated by the problem of forecasting power outages during hurricanes. The extreme nature of the most devastating hurricanes means that typical validation set ups will produce models that underestimate their devastating effects. Our method provides a data‐driven means of adapting a machine learning method to deal with extreme events.

中文翻译：

---

通过局部优化的随机森林预测飓风相关的停电

标准的监督学习程序是根据假设与培训数据分布相同的测试集进行验证的。但是，在许多问题中，测试数据可能来自不同的分布。我们考虑从一个分布P ₁具有许多标记观察值的情况，并希望在来自P _2的未标记点进行预测。我们将随机森林的高预测准确性与重要性采样方案结合在一起，在该方案中，基础树的拆分和预测以加权方式完成，我们称其为局部优化的随机森林。这些权重对应于训练和测试分布之间的似然比的非参数估计。为了用未标记的测试集估计这些比率，我们做出协变量平移假设，其中分布差异仅是训练分布的函数。这种方法是由预测飓风期间的停电问题引起的。最具破坏性的飓风的极端性质意味着典型的验证设置将产生低估其破坏性影响的模型。我们的方法提供了一种数据驱动的方法，可以使机器学习方法适应极端事件。