@inproceedings{344bdadc40114428b4e5842bc911dc00,
title = "A Comparison of the Effects of Data Imputation Methods on Model Performance",
abstract = "Missing values cause critical problems on training a prediction model. Various missing data imputation methods have been introduced to settle down the problem. However, the imputation accuracy obtained by the methods is insufficient to validate performance of prediction models. Thus, in this study, we compare (1) imputation accuracy from various imputation methods as well as (2) the effects of imputation methods on prediction accuracy, investigating a relationship between imputation accuracy and prediction accuracy. For the comparison, we use water quality data composed of the latest actual observational multi-sensor data from Daecheong Lake. We conduct several experiments to compare seven imputation methods including a state of the art method, and their effects on three distinct prediction models. Through quantitative comparison and analysis, we proved that it is necessary to consider both imputation accuracy and model prediction accuracy when choosing an imputation method.",
keywords = "amelia imputation, imputation methods, incomplete data, knn imputation, linear interpolation, mean imputation, mice imputation, missing data, missing values, model performance, randomforest imputation, SVD imputation",
author = "Wooyoung Kim and Wonwoong Cho and Jangho Choi and Jiyong Kim and Cheonbok Park and Jaegul Choo",
year = "2019",
month = apr,
day = "29",
doi = "10.23919/ICACT.2019.8702000",
language = "English",
series = "International Conference on Advanced Communication Technology, ICACT",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "592--599",
booktitle = "21st International Conference on Advanced Communication Technology",
note = "21st International Conference on Advanced Communication Technology, ICACT 2019 ; Conference date: 17-02-2019 Through 20-02-2019",
}