Feedback driven improvement of data preparation pipelines

作者：

Highlights：

• Feedback on results can inform changes to a complete data preparation pipeline.

• The pipeline can include matching, mapping generation and data repair.

• A statistical approach can establish which actions to take based on feedback.

• The same statistical approach can be used to target results for feedback.

摘要

•Feedback on results can inform changes to a complete data preparation pipeline.•The pipeline can include matching, mapping generation and data repair.•A statistical approach can establish which actions to take based on feedback.•The same statistical approach can be used to target results for feedback.

论文关键词：Data preparation,Data wrangling,Extract transform load,Dataspace,Feedback

论文评审过程：Received 29 June 2019, Revised 14 October 2019, Accepted 24 November 2019, Available online 6 December 2019, Version of Record 10 June 2020.

论文官网地址：https://doi.org/10.1016/j.is.2019.101480