Name
Title | ||
|---|---|---|
Research On Economic Recession Prediction Model From The Multiple Behavioral Features Perspective |
Abstract | ||
|---|---|---|
Considering the disadvantages of conventional economic recession methods, such as low efficiency and low generalization, we construct an economic recession prediction model based on the neighborhood rough set (NRS) and support vectors machine (SVM). NRS is first introduced to reduce multiple behavioral features (consumer behavior, work behavior, and residential behavior) of economic recession. The proposed model is examined by the U.S. monthly datasets from January 1959 to December 2016. The results demonstrate that the NRS-SVM model has a high out-of-sample performance than the SVM, probit approach and the overall improvement is 13.65% and 18.79%. Meanwhile, the result shows that the measure of consumer sentiment, work behavior, and residential behavior all have a dynamic impact on the future of economic recession. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/ACCESS.2019.2924267 | IEEE ACCESS |
Keywords | Field | DocType |
Recession forecasting, behavioral features, neighborhood rough set, support machine vector | Data science,Recession,Computer science,Distributed computing | Journal |
Volume | ISSN | Citations |
7 | 2169-3536 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| chang wang | 1 | 33 | 12.55 |
| Zhi Xiao | 2 | 210 | 13.26 |
| Fang-Su Zhao | 3 | 0 | 0.68 |
| Du Ni | 4 | 0 | 0.68 |
| Lue Li | 5 | 0 | 1.01 |