计算机应用 ›› 2014, Vol. 34 ›› Issue (3): 873-878.DOI: 10.11772/j.issn.1001-9081.2014.03.0873

• 行业与领域应用 • 上一篇    下一篇

平滑削边绝对偏离惩罚截断Hinge损失支持向量机的财务危机预报

刘遵雄,黄志强,刘江伟,陈英   

  1. 华东交通大学 信息工程学院,南昌 330013
  • 收稿日期:2013-07-22 修回日期:2013-09-18 出版日期:2014-03-01 发布日期:2014-04-01
  • 通讯作者: 黄志强
  • 作者简介:刘遵雄(1967-),男,江西瑞昌人,教授,博士,主要研究方向:机器学习、数据挖掘;黄志强(1989-),男,江西抚州人,硕士研究生,主要研究方向:机器学习、优化算法;刘江伟(1983-),男,河南许昌人,硕士研究生,主要研究方向:数据挖掘;陈英(1991-),男,江西南昌人,硕士研究生,主要研究方向:聚类算法。
  • 基金资助:

    国家自然科学基金资助项目;教育部人文社会科学研究规划基金项目;华东交通大学2013年度研究生创新专项资金资助项目

Financial failure prediction using truncated Hinge loss support vector machine with smoothly clipped absolute deviation penalty

LIU Zunxiong,HUANG Zhiqiang,LIU Jiangwei,CHEN Ying   

  1. School of Information Engineering, East China Jiaotong University, Nanchang Jiangxi 330013, China
  • Received:2013-07-22 Revised:2013-09-18 Online:2014-03-01 Published:2014-04-01
  • Contact: HUANG Zhiqiang

摘要:

针对传统支持向量机(SVM)分类存在对离群点敏感、支持向量(SV)个数多和分类面参数非稀疏的问题,提出了平滑削边绝对偏离(SCAD)惩罚截断Hinge损失SVM(SCAD-TSVM)算法,并将其用于构建财务预警模型,同时就该模型的求解设计了一个迭代更新算法。结合沪深股市A股制造业上市公司的财务数据进行实证分析,同时对比L1范数惩罚SVM、SCAD惩罚SVM和截断Hinge损失SVM(TSVM)构建的T-2和T-3模型,结果发现SCAD-TSVM构建的T-2和T-3模型都具有最好的稀疏性和最高的预报精度,而且其在不同训练样本数上的平均预测准确率都要比L1范数SVM(L1-SVM)、SCAD-SVM和TSVM算法的高。

关键词: 支持向量机, SCAD惩罚, 截断Hinge损失SVM, 财务预警, L1范数惩罚

Abstract:

Aiming at the problems that the traditional Support Vector Machine (SVM) classifier is sensitive to outliers and has the large number of Support Vectors (SV) and the parameter of its separating hyperplane is not sparse, the Truncated hinge loss SVM with Smoothly Clipped Absolute Deviation (SCAD) penalty (SCAD-TSVM) was put forward and was used for constructing the financial early-warning model. At the same time, an iterative updating algorithm was proposed to solve the SCAD-TSVM model. Experiments were implemented on the financial data of A-share manufacturing listed companies of the Shanghai and Shenzhen stock markets. Compared to the T-2 and T-3 models constructed by SVM with L1 norm penalty (L1-SVM), SVM with SCAD penalty (SCAD-SVM) and Truncated hinge loss SVM (TSVM), the T-2 and T-3 model constructed by the SCAD-TSVM had the best sparseness and the highest accuracy of prediction, and its average accuracies of prediction with different number of training samples were higher than those of the L1-SVM, SCAD-SVM and TSVM algorithms.

Key words: Support Vector Machine (SVM), Smoothly Clipped Absolute Deviation (SCAD) penalty, Truncated hinge loss SVM (TSVM), financial early-warning, L1 norm penalty

中图分类号: