A Conceptual Framework for Post-COVID Financial Distress Prediction Using Fuzzy Inference Systems in Emerging Markets

Abstract

Financial distress prediction has traditionally been based on linear, ratio-driven models that assume stable economic conditions and clear financial signals. However, the COVID-19 pandemic introduced significant uncertainty and uneven recovery patterns, particularly in emerging markets, which challenge these assumptions. In response, this study proposes a conceptual framework for post-COVID financial distress prediction using a Fuzzy Inference System (FIS). Drawing on financial distress theory, decision science, and fuzzy logic, this paper reinterprets key financial ratios—such as profitability, liquidity, leverage, and efficiency—not as precise values, but as flexible and linguistically meaningful indicators. These indicators are then integrated into a rule-based fuzzy inference system to generate a more nuanced assessment of financial distress risk. From a theoretical perspective, the proposed framework shows how fuzzy inference can better capture non-linearity, uncertainty, and the complex interactions between financial variables—areas where traditional linear models often fall short. This study contributes to the financial distress literature by introducing an uncertainty-aware framework that connects corporate finance with intelligent decision-making systems. It also lays a strong foundation for future empirical testing and offers practical insights for regulators, investors, and managers navigating post-crisis environments.