Skip to main content

A structural credit risk model based on purchase order information

June 15, 2018
Suguru Yamanaka*1
Misaki Kinoshita*2

Abstract

This study proposes a credit risk model based on purchase order (PO) information, which is called a "PO-based structural model,"and performs an empirical analysis on credit risk assessment using real PO samples. A time-series model of PO transitions is introduced and the asset value of the borrower firm is obtained using the PO time-series model. Then, we employ a structural framework in which default occurs when the asset value falls below the debt amount, in order to estimate the default probability of the borrower firm. The PO-based structural model enables us to capture borrower firms' precise business conditions on a real-time basis, which is not the case when using only financial statements. With real PO samples provided by some sample firms, we empirically show the effectiveness of our model in estimating default probabilities of the sample firms. One of the advantages of our model is its ability to obtain default probabilities reflecting borrower firms' business conditions, such as trends in PO volumes and credit quality of buyers.

Keywords
Purchase order information; Credit risk, Structural model

  1. *1Department of Mathematical Engineering, Faculty of Engineering, Musashino University
    E-mail : syamana@musashino-u.ac.jp
  2. *2Financial System and Bank Examination Department (currently at Iyo Bank, Ltd.)

Notice

Papers in the Bank of Japan Working Paper Series are circulated in order to stimulate discussion and comments. Views expressed are those of authors and do not necessarily reflect those of the Bank.
If you have any comment or question on the working paper series, please contact each author. When making a copy or reproduction of the content for commercial purposes, please contact the Public Relations Department (post.prd8@boj.or.jp) at the Bank in advance to request permission. When making a copy or reproduction, the source, Bank of Japan Working Paper Series, should explicitly be credited.