BriefGPT.xyz
Aug, 2022
识别和克服预测模型中的转换偏差
Identifying and Overcoming Transformation Bias in Forecasting Models
HTML
PDF
Sushant More
TL;DR
本文研究了预测模型中使用目标变量的对数和平方根变换会引入负偏差的问题，并提出了两种校正方法，通过实验证明校正方法可以提高模型表现，同时也提出了Tweedie回归模型可以作为解决方案之一。
Abstract
Log and square root transformations of target variable are routinely used in
forecasting models
to predict future
sales
. These transformations often lead to better performing models. However, they also introduce
→