Abstract
Classification methods usually exhibit a poor performance when they are applied on imbalanced data sets. In order to overcome this problem, some algorithms have been proposed in the last decade. Most of them generate synthetic instances in order to balance data sets, regardless the classification algorithm. These methods work reasonably well in most cases; however, they tend to cause over-fitting.
In this paper, we propose a method to face the imbalance problem. Our approach, which is very simple to implement, works in two phases; the first one detects instances that are difficult to predict correctly for classification methods. These instances are then categorized into “noisy” and “secure”, where the former refers to those instances whose most of their nearest neighbors belong to the opposite class. The second phase of our method, consists in generating a number of synthetic instances for each one of those that are difficult to predict correctly. After applying our method to data sets, the AUC area of classifiers is improved dramatically. We compare our method with others of the state-of-the-art, using more than 10 data sets.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Esfandiari, N., Babavalian, M.R., Moghadam, A.-M.E., Tabar, V.K.: Review: knowledge discovery in medicine: current issue and future trend. Expert Syst. Appl. 41(9), 4434–4463 (2014)
García, V., Sánchez, J.S., Mollineda, R.A.: On the effectiveness of preprocessing methods when dealing with different levels of class imbalance. Knowl. Based Syst. 25(1), 13–21 (2012). Special Issue on New Trends in Data Mining
He, H., Garcia, E.A.: Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 21(9), 1263–1284 (2009)
Hilas, C.S., Mastorocostas, P.A.: An application of supervised and unsupervised learning approaches to telecommunications fraud detection. Knowl. Based Syst. 21(7), 721–726 (2008)
Lemnaru, C., Potolea, R.: Imbalanced classification problems: systematic study, issues and best practices. In: Zhang, R., Zhang, J., Zhang, Z., Filipe, J., Cordeiro, J. (eds.) ICEIS 2011. LNBIP, vol. 102, pp. 35–50. Springer, Heidelberg (2012)
Sheng, V.S., Gu, B., Fang, W., Wu, J.: Cost-sensitive learning for defect escalation. Knowl. Based Syst. 66, 146–155 (2014)
Sun, J., Li, H., Huang, Q.-H., He, K.-Y.: Predicting financial distress and corporate failure: a review from the state-of-the-art definitions, modeling, sampling, and featuring approaches. Knowl. Based Syst. 57, 41–56 (2014)
Tomasev, N., Mladenic, D.: Class imbalance and the curse of minority hubs. Knowl. Based Syst. 53, 157–172 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
López-Chau, A., García-Lamont, F., Cervantes, J. (2015). Classification on Imbalanced Data Sets, Taking Advantage of Errors to Improve Performance. In: Huang, DS., Han, K. (eds) Advanced Intelligent Computing Theories and Applications. ICIC 2015. Lecture Notes in Computer Science(), vol 9227. Springer, Cham. https://doi.org/10.1007/978-3-319-22053-6_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-22053-6_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-22052-9
Online ISBN: 978-3-319-22053-6
eBook Packages: Computer ScienceComputer Science (R0)