A neural network-based Z-score model for early warning of listed companies’ financial quality
Bibliographic record
Abstract
This paper improves the prediction accuracy of financial crisis of listed companies by optimizing the traditional Z-score model and taking the financial warning indicators as the input features of the neural network.The study selected the financial data of listed companies in a certain place from 2017 to 2023 as a sample, compared and analyzed the early warning performance of multiple traditional machine learning algorithms with this paper's method, and assessed the reliability of this paper's model in the early warning of financial quality by combining with cases.The neural network-based Zscore model has an AUC value of 0.914 on financial quality early warning, which is close to 1, and the prediction results are reliable.The model's overall financial quality early warning accuracy in year t-1 is elevated by 16.61% to 19.35% compared with the comparison algorithm, and has a faster error has convergence speed.The Z-value calculation predicts that three companies will appear to have financial quality risk in 2017, which is consistent with the actual results.The algorithm of this paper predicts that company 9 has a Z-value of 3.79 in 2031, which may have financial quality risk.The results of this paper are reliable and show the early warning method of financial quality of listed companies in a new perspective, which is an important reference value for investors and managers.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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".