Predicting the Distress of Financial Intermediaries using Convolutional Neural Networks
Bibliographic record
Abstract
Over the past 15 years, the United States has faced two major economic events — the 2008 financial meltdown and the 2019 Shadow Bank crisis. Now, it faces a new financial emergency brought on by COVID-19. Financial intermediaries comprise institutions such as banks, mutual funds, insurance companies, real estate investment trusts, among others, and are a significant part of economic stability. “Too big to fail” has become a well-known phrase. Therefore, being able to predict the financial distress of a financial intermediary is very important. Traditionally, the Altman Z-score (or a variation thereof), has been used to predict bankruptcy. It uses 5 key financial ratios to create an index score, or Z-score. Predicting financial distress, however, also accounts for companies that may not be currently on the path to bankruptcy, but may be in the future. Contemporary research has shown that combining sentiment analysis with ratio analysis improves the prediction. Our methodology uses both financial ratios and sentiment, but also includes the London Interbank Offered Rate (LIBOR), and the keywords “Going Concern” and “Concentration Risk”. Using a Convolutional Neural Network, we classified financial intermediaries as either distressed or not distressed with an accuracy of 88.24%.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".