Distributional Feature Separability for Explainability of Neural Networks for Financial Credit Evaluation
Bibliographic record
Abstract
Financial credit evaluation plays an essential role in determining the creditworthiness of applicants. The deep learning models achieve high predictive accuracy, but their black-box nature limits trust, interpretability, and regulatory compliance. Existing explainability methods, such as SHAP and LIME, provide feature attributions but suffer from instability, dependence on external data, and high computational overhead. This paper introduces Distributional Feature Separability (DFS), a deterministic and computationally efficient explainability method based on statistical distance measures to address these limitations. DFS quantifies feature importance by comparing the empirical distributions of feature values across predicted classes, eliminating reliance on gradients, perturbations, and background datasets. We evaluate DFS against SHAP, LIME, and Integrated Gradients using key explanation metrics, including infidelity, sparsity, and sensitivity, across multiple deep learning architectures: Multi-Layer Perceptron, Convolutional Neural Network, Transformer, and Autoencoder. Experimental results show that DFS consistently achieves lower infidelity, higher sparsity, and lower sensitivity while greatly reducing computational cost.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".