Estimating corporate greenhouse gas emissions

This chapter reviews existing machine learning models for estimating scope 1, 2, and 3 greenhouse gas emissions of companies using publicly available data, and develops a new interpretable approach, focusing on out-of-sample evaluation as well as on the data preprocessing steps such as outlier filtering, missing value imputation, and predictor selection. Two frameworks are presented: one without restrictions and another one with fewer inputs, better suited for small and mid-caps and for private companies.