A transformer-based model for default prediction in mid-cap corporate markets
Bibliographic record
Abstract
In this paper, we study mid-cap companies, i.e. publicly traded companies with less than US$10 billion in market capitalisation. Using a large dataset of US mid-cap companies observed over 30 years, we look to predict the default probability term structure over the short to medium term and understand which data sources (i.e. fundamental, market or pricing data) contribute most to the default risk. Whereas existing methods typically require that data from different time periods are first aggregated and turned into cross-sectional features, we frame the problem as a multi-label panel data classification problem. To tackle it, we then employ transformer models, a state-of-the-art deep learning model emanating from the natural language processing domain. To make this approach suitable to the given credit risk setting, we use a loss function for multi-label classification, to deal with the term structure, and propose a multi-channel architecture with differential training that allows the model to use all input data efficiently. Our results show that the proposed deep learning architecture produces superior performance, resulting in a sizeable improvement in AUC (Area Under the receiver operating characteristic Curve) over traditional models. In order to interpret the model, we also demonstrate how to produce an importance ranking for the different data sources and their temporal relationships, using a Shapley approach for feature groups.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".