Water end-use consumption in low-income households: Evaluation of the impact of preprocessing on the construction of a classification model

作者：

Highlights：

• Water consumption variability affects the preprocessing of time series features.

• Random Forest and 1NN with the ERP measure show similar performances.

• Errors linked to preprocess method must be known in order to select that model.

摘要

•Water consumption variability affects the preprocessing of time series features.•Random Forest and 1NN with the ERP measure show similar performances.•Errors linked to preprocess method must be known in order to select that model.

论文关键词：Low-income water end use,Demand management,Random forest model,Adaptive KNN model,ERP measure applied to KNN,Dataset preprocessing

论文评审过程：Received 25 February 2021, Revised 14 July 2021, Accepted 14 July 2021, Available online 19 July 2021, Version of Record 23 July 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115623