Advances and Challenges in Predicting SME Failures: A Literature Review on Methodological Trends, Data Imbalance Solutions, and Model Validation Practices

Rizal, Muhammad
Qalbia, Farah

International Journal of Management, Accounting & Finance
Vol. 2 No. 1 (2025): International Journal of Management, Accounting & Finance (KBIJMAF)

This qualitative literature review explores the advances and challenges in predicting SME failures, focusing on methodological trends, data imbalance solutions, and model validation practices. Over recent years, machine learning techniques have gained prominence, replacing traditional statistical models and improving predictive accuracy. Key strategies for overcoming data imbalance, such as Synthetic Minority Over-sampling Technique (SMOTE) and cost-sensitive learning, have also been highlighted. However, challenges persist, particularly in model interpretability, generalization, and overfitting. The review emphasizes the need for continuous refinement of predictive models and validation practices to ensure real-world applicability. The findings suggest that while considerable progress has been made, future research should aim to enhance model transparency and address limitations in data representation to improve SME failure prediction across diverse contexts.