Study of forecasting system for financial economic data
Project/Area Number |
23500364
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Statistical science
|
Research Institution | The University of Tokyo (2013) The Institute of Statistical Mathematics (2011-2012) |
Principal Investigator |
SATO Seisho 東京大学, 経済学研究科(研究院), 准教授 (60280525)
|
Project Period (FY) |
2011 – 2013
|
Project Status |
Completed (Fiscal Year 2013)
|
Budget Amount *help |
¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
Fiscal Year 2013: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2012: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2011: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
Keywords | 時系列予測 / 多変量自己回帰モデル / 分離情報最尤法 / 季節調整法 / 逐次予測 / X12Decomp / AIC最適化 / ビッグデータ / 制限情報最尤法 / 電力需要予測 / 異常値処理 |
Research Abstract |
In this study, I developed a time series forecasting system for financial economic data from given data sets. Separating Information Maximum Likelihood method was used for robust estimating in the first step, then I utilized Vector Autoregressive models for the predicting models which are optimal in the sense of AIC. It is very important for "Big data" era that this system can be applied for large scaled data. A new knowledge discovery is expected when this method is applied for various economic data and business data.
|
Report
(4 results)
Research Products
(22 results)