Fintech Unicorns Forecaster: An AI Approach For Financial Distress Prediction

Abstract

Purpose: This research undertakes an inquiry into the forecasting of financial distress within the fintech sector, providing valuable insights into the financial health and stability of FinTech unicorns. Through employing an AI technique, a highly accurate financial distress prediction model was created, which also aims to identify and elucidate the pivotal financial variables that influence the prediction of fintech unicorns’ financial distress.

Design/methodology/approach: This study centers on a dataset featuring prominent fintech unicorns and employs Artificial Neural Networks (ANNs) as a methodological analysis method. Fourteen financial ratios were used in this study to gauge their significance in predicting financial distress among FinTech unicorns.

Findings: A classification model was created yielding 95.9% predictive accuracy. In addition, the analysis pinpoints return on capital, current ratio, quick ratio, and the debt-to-equity ratio as significant predictors of financial distress within FinTech unicorns.

Practical Implications: This research substantially contributes to the development of a robust and sustainable FinTech ecosystem. It enhances understanding of the financial landscape, benefiting stakeholders, policymakers, and the broader FinTech community by shedding light on crucial aspects of financial health.

Originality/value: This pioneering study employs ANNs to explore financial distress prediction within the dynamic FinTech sector, providing crucial insights into factors affecting the financial stability of FinTech unicorns.