Financial distress detection using ensemble learning

Wong, Phoebe Hui Lei (2025) Financial distress detection using ensemble learning. Final Year Project, UTAR.

Preview

PDF Download (5Mb) | Preview

Abstract

Financial distress prediction is a crucial role, as an “early warning” for a company to address with the financial risk including restructuring the financial strategies and managing the operating costs effectively. Over time, several approaches have been developed for financial distress predictions, which are methods based on the financial ratios, single classification model and ensemble learning. However, few challenges have been found out from the previous approaches such as the imbalance datasets, limitations on the financial ratios and the auditor biases on selecting financial ratios. In this thesis focuses on ensemble learning are known to capture large and complex datasets and provide more robust result. The aim of the project is to identify the optimal ensemble learning technique in detecting financial distress risk. Area of Study: Financial distress detection, ensemble learning Keywords: Financial distress detection, ensemble learning, financial ratios, bagging, stacking, boosting

Actions (login required)