RESI: A Region-Splitting Imputation method for different types of missing data

作者：

Highlights：

• Only imputing numerical or categorical missing data is unpractical.

• Region-splitting iterative framework (RESI) excels at completing mix-type missing data.

• Mean integrity rate is defined to measure the whole missing degree of a dataset.

• The k-fold validation can alleviate the deviation caused by under- and overlearning.

摘要

•Only imputing numerical or categorical missing data is unpractical.•Region-splitting iterative framework (RESI) excels at completing mix-type missing data.•Mean integrity rate is defined to measure the whole missing degree of a dataset.•The k-fold validation can alleviate the deviation caused by under- and overlearning.

论文关键词：Data mining,Missing data imputation,Region-splitting,k-fold cross validation

论文评审过程：Received 6 June 2019, Revised 29 November 2020, Accepted 29 November 2020, Available online 5 December 2020, Version of Record 9 December 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114425