Verification of generation mechanism of market liquidity risk with conic finance and Limit-order-book process
| Project/Area Number |
17K01248
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Social systems engineering/Safety system
|
|---|
| Research Institution | Hitotsubashi University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
足立 高徳 首都大学東京, 経営学研究科, 教授 (60733722)
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2019: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2018: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 金融リスク / Hawkes過程 / 板情報過程 / 高頻度取引 / 金融工学 / 市場流動性リスク |
|---|
| Outline of Final Research Achievements |
Through this research, we conclude that it will be possible to implement advanced financial risk management such as liquidity stress test using high-frequency transaction data by introducing the concepts of "conic finance" and "limit-order-book(LOB) process," which have not been so popular in Japan.
In addition, we obtain some new knowledge about the following topics related to this research subjects: an application of conic finance to portfolio optimization, an application of multidimensional Hawkes process to credit risk management and high frequency trading, an analysis of cryptocurrency market time-series data, an artificial market generation with some machine learning method for big data, and so on.
|
| Academic Significance and Societal Importance of the Research Achievements |
「錐型ファイナンス」に基づく分析手法やHawkes過程の拡張モデルが、さまざまな金融データの分析に有効であることが実証的にも確認できたことは学術的にはもとより、金融リスク管理という実務への応用に直接つながるという点でも意義があると考えられる。
また「板情報過程」を活用したアルゴリズム取引の実践という点でも、非常に大きなサイズのデータから板情報の再生に必要な情報を効率的に取り出し、敵対的生成ネットワークという技術を用いて、人工的な市場の生成を試みることができたことは、シミュレーションベースのストレステストの実用化という点でも大きな成果であるといえる。
|
Report
(4 results)
Research Products
(31 results)
