| Budget Amount *help |
¥15,990,000 (Direct Cost: ¥12,300,000、Indirect Cost: ¥3,690,000)
Fiscal Year 2022: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Fiscal Year 2021: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Fiscal Year 2020: ¥2,730,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥630,000)
Fiscal Year 2019: ¥8,320,000 (Direct Cost: ¥6,400,000、Indirect Cost: ¥1,920,000)
|
|---|
| Outline of Final Research Achievements |
The present study uses high-frequency time series data on exchange rates. We selected a deep learning model for time series analysis and conducted the analysis. Specifically, we used Long Short-Term Memory (LSTM) to test whether limit order book information in the exchange rate market is effective in predicting exchange rates. The deep learning model's predictive power exceeded that of the existing models, and the limit order information was found to be useful in predicting exchange rates.
|
