Name
Abstract | ||
|---|---|---|
In this article, we start with a brief literature review about using Multivariate Discriminant Analysis (MDA) in bankruptcy prediction. We restrict our attention to the MDA models based on financial ratios. We then designed a group of statistical experiments to test the classic MDA model and its modified version. Both linear discriminant analysis and quadratic discriminant analysis are considered. Experiments are also designed for testing the parameter sensitivity and the stability of the MDA models. Observations from these experiments provide some empirical insights for some of the key issues using MDA in context of bankruptcy prediction, including reducing number of ratios used in the model, and the optimal accounting review intervals. Noise contamination is also taken into account;. The MDA models are also compared with one of the Neural-Networking based model - the SOLAR algorithm. By the end, we remark on how MDA models should be modified to fit in the bankruptcy prediction for e-commerce companies. |
Year | Venue | Keywords |
|---|---|---|
2005 | EEE '05: Proceedings of the 2005 International Conference on E-Business, Enterprise Information Systems, E-Government, and Outsourcing | statistical model |
Field | DocType | Citations |
Data mining,Computer science,Bankruptcy prediction,Statistical model,Artificial intelligence,Machine learning | Conference | 0 |
PageRank | References | Authors |
0.34 | 1 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiaoping Shen | 1 | 19 | 3.67 |
| Jie Gao | 2 | 33 | 8.08 |