Establishment of credit risk assessment methods reflecting various bankruptcy factors

• Project/Area Number: 21K01563
• 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: Aoyama Gakuin University
• Principal Investigator: Yamanaka Suguru 青山学院大学, 理工学部, 准教授 (90804526)
• Project Period (FY): 2021-04-01 – 2024-03-31
• Project Status: Completed (Fiscal Year 2023)
• Budget Amount: ¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000); Fiscal Year 2023: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000); Fiscal Year 2022: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000); Fiscal Year 2021: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
• Keywords: 信用リスク / ファイナンス / 金融リスク管理 / 企業倒産 / 倒産

Outline of Research at the Start

債務超過、資金繰り難、さらに人手不足や取引先破綻などの様々な倒産要因を包括的に取り扱う倒産リスク評価手法の構築を目指す。まず、企業データ分析により倒産発生の特徴抽出を行う。次に、倒産発生のメカニズムを記述する数理モデルの構築を行う。数理モデルの有効性を企業倒産等の実績データとモデル出力値の比較を通して検証する。

Outline of Final Research Achievements

This study presents the credit risk model that can treat not only insolvency, but also cash-short as a bankruptcy state, under the structural-type approach. We also developed the credit risk assessment model with a long-short term memory (LSTM). Through the performance test of the model, we confirmed that financial statement time-series data is useful in credit risk assessment. Furthermore, we constructed a model that predicts the bankruptcy counts based on the business sentiment of corporate managers.

Academic Significance and Societal Importance of the Research Achievements

本研究によって，信用リスク評価の理論的アプローチである構造型信用リスク評価モデルが対象とする倒産事象が拡大した．また，信用リスク評価にあたって，中長期の財務時系列データを用いることの有効性が確認された．これらの成果は，実務における企業評価の高度化に寄与する可能性を有する．

Research Products

• [Journal Article] Relationship between managerial sentiments and corporate bankruptcies (2023)
  • Author(s): Suguru Yamanaka , Takaya Ohsato
  • Journal Title: JSIAM Letters Volume: 15 Issue: 0 Pages: 85-88
  • DOI: 10.14495/jsiaml.15.85
  • ISSN: 1883-0609, 1883-0617
  • Peer Reviewed / Open Access
• [Journal Article] Improvement of Credit Rating Classification Accuracy by using Financial Statements Time-Seriese Data ̃Validation by Long Short-Term Memory Model ̃ (2022)
  • Author(s): 門田 賢征、山中 卓
  • Journal Title: Transactions of the Japan Society for Industrial and Applied Mathematics Volume: 32 Issue: 4 Pages: 133-154
  • DOI: 10.11540/jsiamt.32.4_133
  • ISSN: 2424-0982
  • Peer Reviewed / Open Access
• [Presentation] Gross-revenue based structural credit risk model (2024)
  • Author(s): 中川 秀敏, 山中 卓
  • Organizer: 日本応用数理学会 第20回 研究部会連合発表会
• [Presentation] Gross-revenue-based structural credit risk model (2023)
  • Author(s): Suguru Yamanaka, Hidetoshi Nakagawa
  • Organizer: 10th International Congress on Industrial and Applied Mathematics
  • Int'l Joint Research
• [Presentation] Examining the Default Prediction Power of Corporate Managers' Sentiment (2022)
  • Author(s): 山中卓，大里隆也
  • Organizer: 2021年度冬季JAFEE大会
• [Presentation] 経営者センチメント指標を用いた倒産件数予測の試み (2022)
  • Author(s): 山中卓，大里隆也
  • Organizer: 日本応用数理学会第18回研究部会連合発表会
• [Presentation] 信用格付判別問題に対する回帰結合型ニューラルネットワークモデルの有効性検証 (2021)
  • Author(s): 門田賢征，山中卓
  • Organizer: 日本応用数理学会 2021年度 年会