@inproceedings{50de19f63afb47e6b2b4f3303d26927e,
title = "Dirty-Data Impacts on Regression Models: An Experimental Evaluation",
abstract = "Data quality issues have attracted widespread attentions due to the negative impacts of dirty data on regression model results. The relationship between data quality and the accuracy of results could be applied on the selection of appropriate regression model with the consideration of data quality and the determination of data share to clean. However, rare research has focused on exploring such relationship. Motivated by this, we design a generalized framework to evaluate dirty-data impacts on models. Using the framework, we conduct an experimental evaluation for the effects of missing, inconsistent, and conflicting data on regression models. Based on the experimental findings, we provide guidelines for regression model selection and data cleaning.",
keywords = "Data cleaning, Data quality, Experimental evaluation, Model selection, Regression model",
author = "Zhixin Qi and Hongzhi Wang",
note = "Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG.; 26th International Conference on Database Systems for Advanced Applications, DASFAA 2021 ; Conference date: 11-04-2021 Through 14-04-2021",
year = "2021",
doi = "10.1007/978-3-030-73194-6\_6",
language = "英语",
isbn = "9783030731939",
series = "Lecture Notes in Computer Science",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "88--95",
editor = "Jensen, \{Christian S.\} and Ee-Peng Lim and De-Nian Yang and Wang-Chien Lee and Tseng, \{Vincent S.\} and Vana Kalogeraki and Jen-Wei Huang and Chih-Ya Shen",
booktitle = "Database Systems for Advanced Applications - 26th International Conference, DASFAA 2021, Proceedings",
address = "德国",
}