Financial fraud identification model construction based on topological data analysis
Bibliographic record
Abstract
With the increasing complexity of the financial market, corporate financial fraud events occur frequently, posing a serious challenge to investors and market regulators.Aiming at the limitations of traditional financial fraud recognition methods, this paper constructs a financial fraud recognition model MCN based on the topological data analysis method.The model consists of two parts: the Mapper algorithm and one-dimensional convolutional neural network (1DCNN), which combines the global topology extracted by the Mapper algorithm with the local features of the IDCNN to realize the effective identification of financial fraud samples.In order to evaluate the recognition performance of the model, this paper controls the topological feature extraction method unchanged and the classifier unchanged respectively, and compares the performance of the MCN model with other financial fraud recognition models.The results show that the Acc and F1-score of the MCN-based financial fraud recognition model in this paper are 98.69% and 97.64%, respectively, which are better than other models in both perspectives, proving the superiority of the financial fraud recognition model based on topological data analysis constructed in this paper, and thus providing powerful technical support for the regulation of the financial market and the risk management of enterprises.
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 | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| 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".