TY - JOUR
T1 - The Naïve Associative Classifier with Epsilon Disambiguation
AU - Rangel-Diaz De La Vega, Adolfo
AU - Villuendas-Rey, Yenny
AU - Yanez-Marquez, Cornelio
AU - Camacho-Nieto, Oscar
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2020
Y1 - 2020
N2 - This paper presents the Naïve Associative Classifier with Epsilon disambiguation (NAC), an extension of the Naïve Associative Classifier that, by including a procedure to disambiguate classes in regions where Bayes risk is high, has a positive effect on the performance of the classifiers of the associative approach on several datasets belonging to the financial environment, particularly in terms of credit risk. The experiments conducted to test the NAC were based on 12 datasets composed with financial information and associated with five stages of the credit process: promotion, evaluation, granting, monitoring and recovery. Due to the severe imbalance present in most datasets, the performance of the proposed algorithm was measured using the area under the ROC curve. Likewise, 5× 2 stratified cross validation was made and finally a couple of statistical tests were applied to compare the results. After applying the NAC to the datasets, a successful disambiguation of classes was observed. In the real world this fact could help financial institutions to evaluate the credit applications more effectively and thus, contribute to the mitigation of monetary losses derived from the poor quality of the information.
AB - This paper presents the Naïve Associative Classifier with Epsilon disambiguation (NAC), an extension of the Naïve Associative Classifier that, by including a procedure to disambiguate classes in regions where Bayes risk is high, has a positive effect on the performance of the classifiers of the associative approach on several datasets belonging to the financial environment, particularly in terms of credit risk. The experiments conducted to test the NAC were based on 12 datasets composed with financial information and associated with five stages of the credit process: promotion, evaluation, granting, monitoring and recovery. Due to the severe imbalance present in most datasets, the performance of the proposed algorithm was measured using the area under the ROC curve. Likewise, 5× 2 stratified cross validation was made and finally a couple of statistical tests were applied to compare the results. After applying the NAC to the datasets, a successful disambiguation of classes was observed. In the real world this fact could help financial institutions to evaluate the credit applications more effectively and thus, contribute to the mitigation of monetary losses derived from the poor quality of the information.
KW - Credit-scoring
KW - financial risks
KW - supervised classification
UR - http://www.scopus.com/inward/record.url?scp=85082508756&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2020.2979054
DO - 10.1109/ACCESS.2020.2979054
M3 - Artículo
SN - 2169-3536
VL - 8
SP - 51862
EP - 51870
JO - IEEE Access
JF - IEEE Access
M1 - 9026904
ER -