Predictive Modeling of Financial Distress in Indian Small-Cap Stocks

Kumar, Vivek (2024) Predictive Modeling of Financial Distress in Indian Small-Cap Stocks. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

This study aims at analyzing the capability of different kinds of machine learning algorithms in assessing the impact of financial distress in the context of the highly risky domain of the Indian small-cap stocks that is of significant concern to investors and financial institutions. To compare the effectiveness of the proposed method, the four models mentioned, Logistic Regression, Random Forest, Support Vector Machine (SVM), and Gradient Boosting Machine (GBM) are used to identify the best approach to use in the early identification of firms that are likely to experience financial instability in the future. The results show that the proposed model of SVM is clearly superior: the accuracy of the model for both classes is 92% and an AUC score of 0.9684. Nevertheless, it was found GBM too can achieve high accuracy, equal to 0.96 and high AUC score 0.9160, for the minority class, the performance of the model was poor for recall, which may lead to the difficulty of identifying distressed firms. Logistic Regression and Random Forest had 97% and 96% accuracy respectively but in the case of Financial Distress where accuracy of detecting the minority class is crucial, both models had a very high bias towards the majority class. The study recommends that more research should be done by including extra data sources, examining the combination of various models, and adopting the dynamic update of the model to improve the prediction performance of the model in the future.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Onwuegbuche, Faithful UNSPECIFIED
Uncontrolled Keywords:	Financial distress prediction; Machine learning; Indian small-cap stocks; Gradient Boosting Machine (GBM); Support Vector Machine (SVM); Logistic Regression; Random Forest; Financial risk management
Subjects:	H Social Sciences > HG Finance > Financial Services H Social Sciences > HG Finance > Fintech T Technology > T Technology (General) > Information Technology > Fintech Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in FinTech
Depositing User:	Ciara O'Brien
Date Deposited:	05 Aug 2025 10:42
Last Modified:	05 Aug 2025 10:42
URI:	https://norma.ncirl.ie/id/eprint/8424

Actions (login required)

View Item