Neural network model arma untuk prediksi data finansial =Financial Data Forecasting Using ARMA Model Neural
The main discussion of this paper is on the comparison of properties of different prediction methods, based on Feedforward and Recurrent network. The paper begins with an introduction of the basic of time series processing and discusses Feedforward network as well as Recurrent network. Feedforward a...
Saved in:
| 主要作者: | |
|---|---|
| 格式: | Article NonPeerReviewed |
| 出版: |
[Yogyakarta] : Universitas Gadjah Mada
2005
|
| 主題: | |
| 在線閱讀: | https://repository.ugm.ac.id/18026/ http://i-lib.ugm.ac.id/jurnal/download.php?dataId=801 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 總結: | The main discussion of this paper is on the comparison of properties of different prediction methods, based on Feedforward and Recurrent network. The paper begins with an introduction of the basic of time series processing and discusses Feedforward network as well as Recurrent network. Feedforward and Recurrent networks have been then applied for financial data, composite consumer price indeks of 43 cities in Indonesia.
The Schwarz's Bayesian Criterion (SBC) is the information criterion for comparing different models. A "best" model is the model with the smallest value of SBC. The result of this research show that neural networks construction with one unit in the hidden layer have the smallest value of SBC.
Key words : Feedforward network, Recurrent network, Financial data, SBC |
|---|