Abstract: Financial risk is among the most significant challenges faced by firms in the maritime shipping industry due to its high capital intensity and strong exposure to market fluctuations, particularly in emerging economies such as Vietnam. Therefore, the classification of financial risk plays a crucial role in providing early warning signals, enabling firms to respond proactively and enhance their resilience to potential financial distress. This study employs machine learning techniques, including Random Forest, Extreme Gradient Boosting, and Linear Support Vector Machine, to classify the financial condition of listed maritime shipping firms in Vietnam, using a panel dataset of 25 firms over the period 2015 – 2025. The empirical results confirm the effectiveness of machine learning approaches in financial risk classification, particularly their capability to model nonlinear relationships and complex interactions among financial variables. These findings not only support the early identification of financial distress risk in maritime shipping firms but also provide a scientific basis for the development of early warning systems and the strengthening of financial risk monitoring mechanisms within the industry.

Keywords: Machine learning; classification; financial risk; maritime shipping firms; Random Forest; Support Vector Machine; Extreme Gradient Boosting.