A hybrid approach of DEA, rough set and support vector machines for business failure prediction

2010 ◽  
Vol 37 (2) ◽  
pp. 1535-1541 ◽  
Author(s):  
Ching-Chiang Yeh ◽  
Der-Jang Chi ◽  
Ming-Fu Hsu
2011 ◽  
Vol 230-232 ◽  
pp. 625-628
Author(s):  
Lei Shi ◽  
Xin Ming Ma ◽  
Xiao Hong Hu

E-bussiness has grown rapidly in the last decade and massive amount of data on customer purchases, browsing pattern and preferences has been generated. Classification of electronic data plays a pivotal role to mine the valuable information and thus has become one of the most important applications of E-bussiness. Support Vector Machines are popular and powerful machine learning techniques, and they offer state-of-the-art performance. Rough set theory is a formal mathematical tool to deal with incomplete or imprecise information and one of its important applications is feature selection. In this paper, rough set theory and support vector machines are combined to construct a classification model to classify the data of E-bussiness effectively.


Filomat ◽  
2016 ◽  
Vol 30 (15) ◽  
pp. 4191-4198
Author(s):  
Linwei Zhai ◽  
Jian Qin ◽  
Lean Yu

In the core competence comprehensive evaluation of aviation manufacturing enterprises, exploring the key factors affecting core competence is crucial to improve the competitiveness of the aviation manufacturing enterprises. In this paper, a novel hybrid approach integrating genetic algorithm (GA) and support vector machines (SVM) is proposed to conduct the key factor exploration tasks in the core competitiveness evaluation of aviation manufacturing enterprises. In the proposed hybrid GA-SVM approach, the GA is used for key factor exploration, while SVM is used to calculate the fitness function of the GA method. Using the survey data from Aviation Industry Corporation of China (AVIC), some experiments analysis is conducted to test the effectiveness of the proposed hybrid approach. Empirical results demonstrate that the proposed hybrid GA-SVM approach can be used as an alternative solution to key factor exploration.


Sign in / Sign up

Export Citation Format

Share Document