Enhancing corporate bankruptcy prediction and customer relationship sustainability through CNN-based financial feature transformation
Ali Shahbazi, Nefise Şirzad, Sima Darvishan, Amir Heidari Arash, Zahra Fakhri, Hossein Najafzadeh · 2026
Read Enhancing corporate bankruptcy prediction and customer relationship sustainability through CNN-based financial feature transformation by Ali Shahbazi, Nefise Şirzad, Sima Darvishan, Amir Heidari Arash, Zahra Fakhri, Hossein Najafzadeh (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13328298.txt.
Description
Ali Shahbazi and co-authors turn firm finance data into images so neural networks can flag bankruptcy risk in a 2026 study. Failing firms can no longer serve customers well, so early warning guards client ties too. The team drew on records for tens of thousands of Polish firms.
Filtered finance traits were scaled and laid out as small gray images. Six classic models and five network hybrids then sorted healthy firms from failing ones. Artificially balanced data, which copies rare failing cases, gave the best scores across models. Top ensembles proved very accurate in cross-checks. Banks and partners could use such flags to act sooner.
Catalog record
| CREATOR | Ali Shahbazi, Nefise Şirzad, Sima Darvishan, Amir Heidari Arash, Zahra Fakhri, Hossein Najafzadeh |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 140 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |