Firm dynamics and the performance of transaction partners
| Project/Area Number |
16K03736
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Money/ Finance
|
|---|
| Research Institution | Hitotsubashi University |
|---|
Principal Investigator |
Miyakawa Daisuke 一橋大学, 大学院経営管理研究科, 准教授 (00734667)
|
|---|
| Project Period (FY) |
2016-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2019: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2018: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2017: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2016: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 企業ダイナミクス / 取引関係 / 因果推論 / 機械学習 / 企業パフォーマンス / 因果関係 / 予測 / ネットワーク / 金融論 |
|---|
| Outline of Final Research Achievements |
In this research project, first, I constructed a large size firm-level data augmented by various transaction relationship information consisting of lender banks, venture capital funds, and non-financial investors as well as customer and supplier firms. Second, through the research projects, I established the investment patters of various investors to start-up companies, constructed a high-performance prediction model for firm dynamics, and implemented a machine learning-based causal inference directly targeting the causal effects running from transaction relationships to firm dynamics, the last of which is the exact target of this research project.
As an important outcome of the research project, I applied two patent applications accounting for (i) the high-performance prediction model for firm dynamics and (ii) the accounting item-level detection model for firms' accounting fraud, both of this have been accepted by Japan Patent Office.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究は、企業の有する取引関係が企業ダイナミクスに対してどのような因果効果を有するかを実証的に明らかにしたものである。取引関係は企業自身の属性からも影響を受けるため、上記因果効果の識別に当たっては分析上の工夫が必要となる。本研究課題では、未上場企業を含む企業レベルデータへ金融機関、販売先、仕入先との取引関係情報を付加した大規模データを構築した上で、ネットワーク科学などの分野で蓄積されてきた機械学習手法を用いることでアプローチした。こうした学際的な取り組みに関する学術的意義に加えて、実務で利用可能な二件の特許取得に繋がったことは本研究課題の実施が社会的な意義を有することを意味している。
|
Report
(5 results)
Research Products
(37 results)
