We model default with novel loan data maintained by the Portuguese Central Bank for 31,025 accounts of privately-held firms that include 30 accounting ratios and non-accounting information on size, age, industry and geographic regions. Interest costs to gross income, number of days in payables and receivables have a positive and significant influence on the probability of default. Financial and asset coverage, the investment ratio, return on equity and investment, solidity, variation in gross income and working capital to total assets are negatively related to default. Interest costs to gross income, solidity and working capital to total assets show larger marginal influence on the probability of default compared to return on investment, financial coverage, days in payables, days in receivables, and return on equity. Asset coverage, investment ratio and variation in gross income show relatively low marginal influence. While size influences default positively, age influences default negatively. The analysis of the joint influence of size and accounting ratios shows that size significantly alters the relation and the magnitude of the marginal influence of the accounting ratios on default. Our findings also indicate that industry and geography influence default. Besides assessing default in privately-held firms, our study identifies the important role of non-accounting information on default prediction and the practical significance of assessing the marginal influence of predictors instead of the classical coefficients. The factors we find as influencing default can be used as early warning signals in policies underlying supervision, and the default probabilities in the assessment of financial pressures in the corporate sector.