使用xgboost进行分类时，如何获得置信区间或预测离散度的度量? [英] How to obtain a confidence interval or a measure of prediction dispersion when using xgboost for classification?

问题描述

使用xgboost进行分类时如何获得置信区间或预测离散度的度量?

How to obtain a confidence interval or a measure of prediction dispersion when using xgboost for classification?

例如，如果xgboost预测某个事件的概率为0.9，那么如何获得对该概率的置信度?

So for example, if xgboost predicts a probability of an event is 0.9, how can the confidence in that probability be obtained?

这个信心也被认为是异方差的吗?

Also is this confidence assumed to be heteroskedastic?

推荐答案

要生成xgboost模型的置信区间，您应该训练几个模型(可以为此使用装袋).每个模型都会对测试样本产生一个响应-所有响应都将形成一个分布，您可以使用该分布轻松地使用基本统计信息计算置信区间.您应该为每个测试样本生成响应分布.

To produce confidence intervals for xgboost model you should train several models (you can use bagging for this). Each model will produce a response for test sample - all responses will form a distribution from which you can easily compute confidence intervals using basic statistics. You should produce response distribution for each test sample.

这篇关于使用xgboost进行分类时，如何获得置信区间或预测离散度的度量?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！