Prediction of Financial Distress Using Dynamic Artificial Neural Network for Early Warning System
Abel M. Nyabera *
Department of Mathematics, Multimedia University of Kenya, Kenya.
Cynthia Ikamari
Department of Finance and Accounting, Multimedia University of Kenya, Kenya.
George Mocheche
Department of Mathematics, Multimedia University of Kenya, Kenya.
*Author to whom correspondence should be addressed.
Abstract
In Kenya's economic landscape, financial hardship is a growing concern, leading to the closure of organizations as they are unable to meet their financial obligations and expectations. This study presents a financial distress prediction dynamic model using Artificial Neural Networks (ANN) using financial ratios as input features where each node represents a single financial metric utilizing there power in measuring financial health of an organization to address this issue. The perceived dynamic ANN model, which is modeled to be adaptable, scalarable and adjustable with the ability self-update its architectures and parameters achieved a 94% accuracy, with strong recall and precision of 92% showing predicted financially distressed instances that were actually distressed. Further, the model demonstrated an ROC-AUC score of 0.99, demonstrating its effectiveness in distinguishing between distressed and non-distressed instances. The model's balanced F1 score of 87% further highlights its value as an Early Warning System (EWS) for financial management, helping organizations make informed decisions and avoid financial crises.
Keywords: Artificial neural networks, financial ratios, early warning systems, financial distress