Bankruptcy analysis using images and convolutional neural networks (CNN)

TL;DR

This paper introduces a novel approach using images and CNNs to predict bankruptcy risk in SMEs, achieving high accuracy and addressing a gap in traditional risk analysis methods.

Contribution

It presents a new image-based method for SME bankruptcy prediction using CNNs, expanding risk analysis beyond publicly traded companies.

Findings

Achieved 97.8% prediction accuracy with the CNN model.

Generated over 10,000 images representing different companies.

Demonstrated the potential for broader applications of image-based risk analysis.

Abstract

The marketing departments of financial institutions strive to craft products and services that cater to the diverse needs of businesses of all sizes. However, it is evident upon analysis that larger corporations often receive a more substantial portion of available funds. This disparity arises from the relative ease of assessing the risk of default and bankruptcy in these more prominent companies. Historically, risk analysis studies have focused on data from publicly traded or stock exchange-listed companies, leaving a gap in knowledge about small and medium-sized enterprises (SMEs). Addressing this gap, this study introduces a method for evaluating SMEs by generating images for processing via a convolutional neural network (CNN). To this end, more than 10,000 images, one for each company in the sample, were created to identify scenarios in which the CNN can operate with higher assertiveness and reduced training error probability. The findings demonstrate a significant predictive capacity, achieving 97.8% accuracy, when a substantial number of images are utilized. Moreover, the image creation method paves the way for potential applications of this technique in various sectors and for different analytical purposes.