Accuracy Comparison Between Feedforward Neural Network, Support Vector Machine and Boosting Ensembles for Financial Risk Evaluation
Bibliographic record
Abstract
Loan defaults have become an increasing concern for lending institutions, presenting significant challenges to profitability and operational stability. However, with the advent of advanced data processing capabilities, greater data availability, and the development of sophisticated machine learning techniques—particularly neural networks—new opportunities have emerged for classifying and predicting loan defaults beyond traditional manual methods. This, in turn, can reduce risk and enhance overall financial performance. In recent years, institutions have increasingly employed these advanced techniques to mitigate the risk of non-performing loans (NPLs) by improving loan approval efficiency. This study aims to address a gap in the literature by examining the predictive performance of different neural network architectures on financial loan datasets. Specifically, it compares the effectiveness of Feedforward Neural Networks (FNNs), Long Short-Term Memory (LSTM) networks, and one-dimensional Convolutional Neural Networks (1D-CNNs) in forecasting loan defaults. Despite the growing body of research in this area, comparative studies focusing on the application of various neural network techniques to loan default prediction remain relatively scarce.
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 | 0.005 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".