Research on Financial Loan Default Prediction Based on Multi-Model Ensemble and Custom Thresholds
Bibliographic record
Abstract
Loan defaults pose significant threats to financial institutions' financial stability and reputation. Although existing risk assessment models have addressed this issue to some extent, they exhibit significant limitations when dealing with large-scale, high-dimensional data. Therefore, developing an advanced model that can predict loan defaults with higher accuracy is crucial. This paper aims to optimize loan default prediction by combining innovative algorithms and models to enhance the risk management capabilities of financial institutions and reduce economic losses. This study proposes a loan default prediction model based on the LendingClub dataset. The model integrates multiple machine learning algorithms, including Logistic Regression, Random Forest, Gradient Boosting, LightGBM, and CatBoost, as well as ensemble learning methods, aiming to improve the prediction accuracy and stability of the model. Through a comprehensive analysis of the model's precision, recall, and custom evaluation metrics, this paper establishes an optimized comprehensive model, improving recall from 60% to 80% and precision from 28% to 29%. By optimizing thresholds, the model significantly enhances the identification of bad loans while balancing precision and recall, providing an effective solution for loan default prediction.
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 | 0.003 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".