Using Imputation Techniques to Help Learn Accurate Classifiers
- Xiaoyuan Su
- Taghi Khoshgoftaar, Computer Science and Engineering, Florida Atlantic University, Boca Raton FL 33431, USA
- Russ Greiner, Dept of Computing Science; PI of AICML
It is difficult to learn good classifiers when training data is missing attribute values. Conventional techniques for dealing with such omissions, such as mean imputation, generally do not significantly improve the performance of the resulting classifier. We proposed imputation-helped classifiers, which use accurate imputation techniques, such as Bayesian multiple imputation (BMI), predictive mean matching (PMM), and Expectation Maximization (EM), as preprocessors for conventional machine learning algorithms. Our empirical results show that EM-helped and BMI-helped classifiers work effectively when the data is "missing completely at random", generally improving predictive performance over most of the original machine learned classifiers we investigated.
Citation
X. Su, T. Khoshgoftaar, R. Greiner. "Using Imputation Techniques to Help Learn Accurate Classifiers". Fifteenth IEEE International Conference on Tools with Artificial Intelligence (ICTAI), pp 437-444, November 2008.| Keywords: | machine learned classifiers, imputation techniques, incomplete data |
| Category: | In Conference |
BibTeX
@incollection{Su+al:ICTAI08,
author = {Xiaoyuan Su and Taghi Khoshgoftaar and Russ Greiner},
title = {Using Imputation Techniques to Help Learn Accurate Classifiers},
Pages = {437-444},
booktitle = {Fifteenth IEEE International Conference on Tools with Artificial
Intelligence (ICTAI)},
year = 2008,
}Last Updated: February 08, 2009Submitted by Xiaoyuan Su
