Despite their popularity, monitoring methods using only financial statements do not provide a real-time stream of changes in business conditions. To address this, our paper proposes a credit risk model based on purchase order (PO) information, also termed a “PO-based structural model”. It performs an empirical analysis of credit risk assessment using real PO samples. A time series model of PO volumes is introduced, and the asset value of the borrower firm is obtained using the PO time series model. To estimate the default probability of the borrower firm we then employ a structural framework where default occurs when the asset value falls below the debt amount. Finally, we show empirically the model’s effectiveness in estimating the default probabilities of the sample firms.