Abstract
This research is aimed at establishing the diagnosis models for business crises through integrating a real-valued genetic algorithm to determine the optimum parameters and SVM to perform learning and classification on data. After finishing the training processes, the proposed GA-SVM can reach a prediction accuracy of up to 95.56% for all the tested business data. Particularly, only six influential features are included in the proposed model with intellectual capital and financial features after the 2-phase selecting process; the six features are ordinary and widely available from public business reports. The proposed GA-SVM is available for business managers to conduct self-diagnosis in order to realize whether business units are really facing a crisis.
Original language | English |
---|---|
Pages (from-to) | 1145-1155 |
Number of pages | 11 |
Journal | Expert Systems With Applications |
Volume | 35 |
Issue number | 3 |
DOIs | |
Publication status | Published - 2008 Oct |
All Science Journal Classification (ASJC) codes
- General Engineering
- Computer Science Applications
- Artificial Intelligence