Abstract
Predicting financial distress is crucial for stakeholders, policymakers, governments, and management in decisionmaking processes. Researchers have developed various prediction models encompassing both traditional and machinelearning approaches. Notably, recent attention has shifted towards employing machine learning models to address the limitations of traditional methods. This study seeks to offer insights into current trends, identify gaps, and suggest future research directions using machine learning models for financial distress prediction, employing the PRISMA Extension for Scoping Reviews methodology. To achieve this, a comprehensive search was conducted across three databases—Science Direct, EBSCO, and ProQuest—spanning from 2020 to 2023, identifying 34 relevant articles for analysis. The findings underscore the prevalent use of Support Vector Machine in financial distress prediction, followed by the Random Forest Classifier and Artificial Neural Network, with little attention paid to other models. Furthermore, the study underscores the necessity for more research in developing countries, noting the predominance of studies from developed nations. While machine learning models hold promise for enhancing the accuracy and efficiency of financial distress prediction, additional research is imperative to evaluate their effectiveness and applicability across diverse contexts. This scoping review aims to furnish researchers, policymakers, and institutions with valuable insights and policy recommendations, shedding light on underexplored machine-learning techniques.
Keywords: Artificial Neural Networks, Financial Distress Prediction, Machine Learning, Support Vector Machine.