2022 Fiscal Year Final Research Report
Statistical inferences for network time series models with geometrical restrictions and their applications to financial martkets
| Project/Area Number |
18K01706
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 07060:Money and finance-related
|
|---|
| Research Institution | Nanzan University (2021-2022)
Tokyo University of Science (2018-2020) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2018-04-01 – 2023-03-31
|
| Keywords | 方向統計学 / 金融市場分析 / ネットワークモデル / 空間統計モデル |
|---|
| Outline of Final Research Achievements |
There is growing interest in applying statistical models and methods to the data and models that are restricted to some geometric structures of the state spaces or parameter spaces. In this research topic, we have studied various aspects of models and methods in statistical approaches in data sciences. First, we consider the performance of portfolios based on the risk-parity strategy. Second, we proposed a skew-symmetric probability distribution family and studied the proposed models' statistical properties. Thirdly, we have developed and evaluated data analysis methods with geometrical parameters and data structures, such as spatial statistical models and recommendation systems.
|
| Free Research Field |
統計学
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究により, 幾何構造をもつさまざまな統計モデルの金融市場分析, 不動産市場分析, 情報サービスへの応用可能性があきらかにされた. これらの基礎研究に基づいた高度なAI手法や, データサイエンスへの展開が期待できることは大きな意義がある. また, 方向統計学における, 一連の歪対称分布の統計的性質に関する学術的成果は, 超球面上あるいは, 高度に複雑な多様体上の確率モデルの発展の基礎を与える研究成果である.
|
