Using Self-Organizing Maps for Binary Classification with Highly Imbalanced Datasets
Cited by
Export citation
- BibTex
- RIS
- TXT
@Article{IJNAMB-5-238,
author = {VINICIUS ALMENDRA AND DENIS EN ̆ACHESCU},
title = {Using Self-Organizing Maps for Binary Classification with Highly Imbalanced Datasets},
journal = {International Journal of Numerical Analysis Modeling Series B},
year = {2014},
volume = {5},
number = {3},
pages = {238--254},
abstract = {Highly imbalanced datasets occur in domains like fraud detection, fraud prediction, and clinical diagnosis of rare diseases, among others. These datasets are characterized by the
existence of a prevalent class (e.g. legitimate sellers) while the other is relatively rare (e.g. fraudsters).
Although small in proportion, the observations belonging to the minority class can be of a
crucial importance. In this work we extend an unsupervised learning technique-Self-Organizing
Maps-to use labeled data for binary classification under a constraint on the proportion of false
positives. The resulting technique was applied to two highly imbalanced real datasets, achieving
good results while being easier to interpret.},
issn = {},
doi = {https://doi.org/},
url = {http://global-sci.org/intro/article_detail/ijnamb/232.html}
}
TY - JOUR
T1 - Using Self-Organizing Maps for Binary Classification with Highly Imbalanced Datasets
AU - VINICIUS ALMENDRA AND DENIS EN ̆ACHESCU
JO - International Journal of Numerical Analysis Modeling Series B
VL - 3
SP - 238
EP - 254
PY - 2014
DA - 2014/05
SN - 5
DO - http://doi.org/
UR - https://global-sci.org/intro/article_detail/ijnamb/232.html
KW - unsupervised learning
KW - self-organizing maps
KW - imbalanced datasets
KW - supervised learning
AB - Highly imbalanced datasets occur in domains like fraud detection, fraud prediction, and clinical diagnosis of rare diseases, among others. These datasets are characterized by the
existence of a prevalent class (e.g. legitimate sellers) while the other is relatively rare (e.g. fraudsters).
Although small in proportion, the observations belonging to the minority class can be of a
crucial importance. In this work we extend an unsupervised learning technique-Self-Organizing
Maps-to use labeled data for binary classification under a constraint on the proportion of false
positives. The resulting technique was applied to two highly imbalanced real datasets, achieving
good results while being easier to interpret.
VINICIUS ALMENDRA AND DENIS EN ̆ACHESCU. (2014). Using Self-Organizing Maps for Binary Classification with Highly Imbalanced Datasets.
International Journal of Numerical Analysis Modeling Series B. 5 (3).
238-254.
doi:
Copy to clipboard