Journal article 437 views
Topological applications of multilayer perceptrons and support vector machines in financial decision support systems
,
Chi Guotai,
Fahmida-E- Moula,
A.S.M. Sohel Azad,
Mohammed Shamim Uddin Khan
International Journal of Finance & Economics, Volume: 24, Issue: 1, Pages: 474 - 507
Swansea University Author:
Mohammad Abedin
Full text not available from this repository: check for access using links below.
DOI (Published version): 10.1002/ijfe.1675
Abstract
The heart of this study is particularly on risk assessment of financial decision support systems (FDSSs), to advance the model performance and improve classification accuracy. To conquer the downsides of the classical models, statistical intelligence (SI) technologies, for example, multilayer percep...
| Published in: | International Journal of Finance & Economics |
|---|---|
| ISSN: | 1076-9307 |
| Published: |
Wiley
2019
|
| Online Access: |
Check full text
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa64237 |
| Abstract: |
The heart of this study is particularly on risk assessment of financial decision support systems (FDSSs), to advance the model performance and improve classification accuracy. To conquer the downsides of the classical models, statistical intelligence (SI) technologies, for example, multilayer perceptrons (MLPs) and support vector machines (SVMs), have been deliberated in FDSS applications. Recently, the prestigiousness of SI approaches has been confronted by the latest prediction learners. Therefore, to ensure the competitive performance of SI mechanisms, the current investigation scrutinizes the topological applications of MLPs and SVMs over eight different databases with equivalent combinations in credit scoring and bankruptcy predictions example sets. The experimental results reveal that MLP5-5 and MLP4-4, that is, the sigmoid activation function with five and four hidden layers, are the feasible topologies for the MLP algorithm, and on all databases in all performance criterions, SVM trained with the linear kernel function (SVM-1) achieves better prediction results. From the “Baseline” family, random forest learner brings significant improvements in financial decisions. Lastly, FDSSs are found to be correlated with the nature of databases and the performance criterions of the trained algorithms. The results of this study, however, have practical and managerial implications to make a range of financial and nonfinancial strategies. With these contributions, therefore, our study not only supplements earlier evidence but also enhances the predictive performance of SI algorithms for financial decision support applications. |
|---|---|
| Keywords: |
Bankruptcy predictions, credit scoring, financial decision support systems, multilayer perceptrons, statistical intelligence, support vector machines, topological applications |
| College: |
Faculty of Humanities and Social Sciences |
| Funders: |
Key Projects of National Natural Science Foundation of China (Grant Numbers: 71731003, 71431002), General Projects of National Natural Science Foundation of China (Grant Numbers: 71471027, 71873103), National Social Science Foundation of China (Grant Number: 16BTJ017), Youth Project of National Natural Science Foundation of China (Grant Numbers: 71601041, 71503199). |
| Issue: |
1 |
| Start Page: |
474 |
| End Page: |
507 |