Research on internal financial fraud identification model of enterprise based on ensemble learning
Bibliographic record
Abstract
In recent years, financial fraud cases have been on the rise, prompting numerous scholars to explore relevant fields and contribute significantly to the practical oversight of the economy. Integrated learning models have also gained widespread application in the realm of financial fraud detection, proving their efficacy in identification. This paper provides a summary of existing research and methodologies employed by scholars. After reviewing pertinent literature, the Logistic Regression model, a Single Decision Tree, Gradient Boosting Decision Trees, Random Forest model, XGBoost model, and LightGBM model were selected as candidate models for studying financial fraud detection. A comparative analysis of their respective identification accuracies was conducted. The research findings indicate that across the overall detection models, the identification rates of all models exceed 70%. Among these, the XGBoost model exhibits the best performance, achieving an identification accuracy of 87.77%. From the comparative results, it is evident that the accuracy of ensemble learning models generally surpasses that of traditional classification models and basic machine learning models, effectively enhancing the efficiency of financial fraud detection. Furthermore, in terms of identification speed, ensemble learning models demonstrate advantages such as shorter processing times and the ability to accommodate larger datasets.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 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".