In recent years, due to the financial crisis, the COVID-19 pandemic, and geopolitical conflicts, corporate financial distress has evolved dramatically. The large number of bankruptcies and the increase of default risk have raised the interest for financial distress prediction models. Financial distress prediction models allow assessing the future ability of firms to meet their obligations and to evaluate the firms' credit risk. Prior research finds two approaches to predict the likelihood of firm's default: accounting-based bankruptcy prediction models and market-based bankruptcy prediction models. These models use historical financial statements and market data to assess future firm's performance. These approaches assume that the information provided by both financial statements and financial markets are reliable and enough to assess the financial health of firms. Particularly, these studies provide evidence that other variables could affect the firm's future performance and solvency (intangibles, audit, corporate governance). Given the limitation of the information used to predict financial distress, this study attempts to investigate whether and how different financial and non-financial variables influence corporate financial distress prediction.
This study can have relevant practical implications for banks, investors, analysts, chief financial officers (CFOs), and managers in general which are interested in bankruptcy prediction. Hence, new explanatory variables improve the predictive power of financial distress prediction models reducing type II error rate. This implies a significant reduction of costs for financial institutions and creditors and improve the efficiency of investor's decisions. Moreover, financial distress prediction models are critical tools for Chief Financial Officers in enabling proactive risk management, supporting strategic decision-making, and avoiding firm's bankruptcy.
Additionally, this research aligns with the European Union's recent recommendations for enhancing early warning systems and financial distress prediction. This study therefore addresses the issues that are timely and of great interest for the scientific community and policy makers.

Velia Gabriella Cenciarelli is Assistant Professor of Accounting at the School of Banking, Finance and Insurance Sciences of Catholic University of the Sacred Heart of Milan. Her main research interests are focused on financial accounting, bankruptcy prediction and credit risk. She has published papers in leading academic journals. She is member of the editorial board and ad hoc referee for National and International journals.