Research on medical insurance fraud identification method based on multi-source datasets
Bibliographic record
Abstract
Due to the fact that datasets pertaining to health insurance are typically stored in different departments and involve multiple databases, conventional data analysis and traditional fraud research methods often fall short in accurately identifying fraudulent activities. To address this challenge, this paper, on one hand, starts by recognizing the unique characteristics of various collected datasets. It employs a multi-source data fusion approach, initially combining their features. Subsequently, an exploratory data analysis is conducted on the fused dataset. Compared to previous single datasets, the merged dataset contains more features, significantly enhancing the model's fitting performance. This approach maximizes the utilization of information within the data, allowing for better exploitation of the data's potential.On the other hand, this paper integrates the strategy of active learning with traditional logistic regression methods, constructing a novel model. The model is initially trained on labeled datasets, and after multiple experiments, it was observed that the fitting accuracy of the active learning model, constructed using the BT strategy (a type of active learning sample extraction strategy), surpassed that of a standalone logistic regression model. This innovative approach provides a new avenue for improving the accuracy of health insurance fraud detection.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.013 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.008 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".