Analysis of the generating and collapsing process of financial bubbles using high frequency stock market data and web-mined text data
| Project/Area Number |
23330108
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Public finance/Monetary economics
|
|---|
| Research Institution | Osaka City University |
|---|
Principal Investigator |
TAKADA Teruko 大阪市立大学, 大学院経営学研究科, 准教授 (30347504)
|
|---|
| Project Period (FY) |
2011-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥18,980,000 (Direct Cost: ¥14,600,000、Indirect Cost: ¥4,380,000)
Fiscal Year 2015: ¥5,460,000 (Direct Cost: ¥4,200,000、Indirect Cost: ¥1,260,000)
Fiscal Year 2014: ¥5,720,000 (Direct Cost: ¥4,400,000、Indirect Cost: ¥1,320,000)
Fiscal Year 2013: ¥5,850,000 (Direct Cost: ¥4,500,000、Indirect Cost: ¥1,350,000)
Fiscal Year 2012: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2011: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
|
|---|
| Keywords | 金融バブル / テキストマイニング / 高頻度データ / 投資家行動 / ネットワーク分析 |
|---|
| Outline of Final Research Achievements |
Aiming at finding new empirical facts useful for clarifying the mechanism of financial bubble generation and collapse, this study targets web-mined message board text data and very long high frequency stock market data. Applied methods to those data are efficient and fully data adaptive such as LDA topic model and nonparametric adaptive kernel density estimation based methods. This study revealed several new empirical facts including those useful for forecasting trend reversals and relationship between stock market status indicated by numerical stock market data and the content of investors’ attention captured by web-mined text data.
|
Report
(6 results)
Research Products
(20 results)
