@inproceedings{17d9d36222154d69b2596e89235aa63f,
title = "Decision tree rule-based feature selection for large-scale imbalanced data",
abstract = "A class imbalance problem often appears in many real world applications, e.g. fault diagnosis, text categorization, fraud detection. When dealing with a large-scale imbalanced dataset, feature selection becomes a great challenge. To confront it, this work proposes a feature selection approach based on a decision tree rule. The effectiveness of the proposed approach is verified by classifying a large-scale dataset from Santander Bank. The results show that our approach can achieve higher Area Under the Curve (AUC) and less computational time. We also compare it with filter-based feature selection approaches, i.e., Chi-Square and F-statistic. The results show that it outperforms them but needs slightly more computational efforts.",
keywords = "Decision tree, feature selection, large-scale imbalanced data",
author = "Haoyue Liu and Mengchu Zhou",
year = "2017",
month = may,
day = "15",
doi = "10.1109/WOCC.2017.7928973",
language = "English (US)",
series = "2017 26th Wireless and Optical Communication Conference, WOCC 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2017 26th Wireless and Optical Communication Conference, WOCC 2017",
address = "United States",
note = "26th Wireless and Optical Communication Conference, WOCC 2017 ; Conference date: 07-04-2017 Through 08-04-2017",
}