• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Development of a Practically Usable Highly Accurate LGD Estimation Model Using the Integrated Database of Regional Banks

Research Project

Project/Area Number 18K12873
Research Category

Grant-in-Aid for Early-Career Scientists

Allocation TypeMulti-year Fund
Review Section Basic Section 07080:Business administration-related
Research InstitutionWaseda University

Principal Investigator

Tanoue Yuta  早稲田大学, 商学学術院(ビジネス・ファイナンス研究センター), 助教 (60805050)

Project Period (FY) 2018-04-01 – 2022-03-31
Project Status Completed (Fiscal Year 2021)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2020: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2019: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Keywords信用リスク / ファイナンス / デフォルト時損失率 / 金融リスク / Loss given default / 変数選択 / LGD / 転移学習 / ビックデータ
Outline of Final Research Achievements

The Basel accords, which aim to strengthen the soundness of the international financial system, require banks to estimate various risks and accumulate capital to cover them. This study was conducted to improve the estimation accuracy of credit risk of bank claims, especially LGD estimation. The results of this study confirm the usefulness of nonlinear models in LGD estimation. We also tested the effectiveness of transfer learning, macroeconomic variables, and business history. We also conducted research on variable selection methods in LGD estimation, which involves a large number of explanatory variables.

Academic Significance and Societal Importance of the Research Achievements

1.海外においては様々なLGD研究は行われてきたが、これまでは日本においてはほとんどLGD研究が行われてこなかった。特に地方銀行の債権のLGD研究は殆ど行われておらず、日本の債権のLGD推定の要因分析に関して検証が十分に行われてこなかった背景がある。本研究は様々な要因の分析が初めて行われた研究である。また、機械学習モデルや転移学習等、信用リスクの分野においてこれまであまり用いられてこなかった方法に関して検証したことに意義があると考えられる。これらの成果を応用することで日本、海外問わず、研究者や実務家がより推定精度の高いLGD推定モデルの開発が可能となり、リスク管理の高度化に資すると考えられる。

Report

(5 results)
  • 2021 Annual Research Report   Final Research Report ( PDF )
  • 2020 Research-status Report
  • 2019 Research-status Report
  • 2018 Research-status Report
  • Research Products

    (3 results)

All 2020 2019 2018

All Journal Article (2 results) (of which Peer Reviewed: 1 results) Presentation (1 results)

  • [Journal Article] Comparison study of two-step LGD estimation model with probability machines2020

    • Author(s)
      Tanoue Yuta、Yamashita Satoshi、Nagahata Hideaki
    • Journal Title

      Risk Management

      Volume: 22 Issue: 3 Pages: 155-177

    • DOI

      10.1057/s41283-020-00059-y

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] Oracle inequalities for sign constrained generalized linear models2019

    • Author(s)
      Koike Yuta、Tanoue Yuta
    • Journal Title

      Econometrics and Statistics

      Volume: 11 Pages: 145-157

    • DOI

      10.1016/j.ecosta.2019.02.001

    • Related Report
      2019 Research-status Report
  • [Presentation] Loss given default estimation for corporation loans: combining a two-stage model with classification tree-based boosting and support vector regression with logistic transformation2018

    • Author(s)
      Yuta Tanoue
    • Organizer
      Waseda International Symposium “Introduction of General Causality to Various Data & its Innovation of the Optimal Inference
    • Related Report
      2018 Research-status Report

URL: 

Published: 2018-04-23   Modified: 2023-12-25  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi