Name
Abstract | ||
|---|---|---|
Unlike the previous study, an optimized neutral model, a new evolutionary calculation method, is applied in this study to predict the net value of domestic mutual funds. Firstly, 17 open-end balanced stock funds data will be collected from domestic securities companies’ websites. Funds with the technical efficiency value of 1 will be selected as investment targets to analyze fund performance by using data envelopment analysis. Then, the mutual fund net worth prediction model is built by various new data mining methods including Backpropagation Neural Network and GABPN, and the forecasting ability is compared with the traditional regression model. We can understand the pros and cons of these fund forecasting models after using five kinds of forecast performance evaluation indicators and analyzing rate of return, and the result of which is available for reference to researchers and investors as an investment strategy. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1007/s10586-018-2272-2 | Cluster Computing |
Keywords | DocType | Volume |
Backpropagation Neural Network, GABPN, Decision tree, Data envelopment analysis, Mutual fund | Journal | 22 |
Issue | ISSN | Citations |
Supplement | 1573-7543 | 5 |
PageRank | References | Authors |
0.73 | 2 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wen-Tsao Pan | 1 | 5 | 0.73 |
| Shi-Zhuan Han | 2 | 5 | 0.73 |
| Hui-Ling Yang | 3 | 5 | 0.73 |
| Xue-ying Chen | 4 | 5 | 1.07 |