Addressing remitting behavior using an ordinal classification approach
作者：
Highlights：
• SVM-based classifiers work well to analyze the remitting behavior of immigrants.
• Ordinal SVM classifiers outperform nominal ones (logistic regression, ANN and SVM).
• Remitting profiles are drawn from the support vectors of the SVMOP classifier.
• Misclassified patterns are analyzed based on the projection of SVOREX results.
• Banks that apply ordinal SVM-based approach can achieve competitive advantage.
摘要
•SVM-based classifiers work well to analyze the remitting behavior of immigrants.•Ordinal SVM classifiers outperform nominal ones (logistic regression, ANN and SVM).•Remitting profiles are drawn from the support vectors of the SVMOP classifier.•Misclassified patterns are analyzed based on the projection of SVOREX results.•Banks that apply ordinal SVM-based approach can achieve competitive advantage.
论文关键词：Nominal classification,Ordinal classification,Support Vector Machine,Remittances
论文评审过程：Available online 18 February 2014.
论文官网地址：https://doi.org/10.1016/j.eswa.2014.01.036
