Research on intelligent financial statement analysis and anomaly identification technology based on machine learning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
In order to accurately assess the financial status of a company and identify potential anomalies, this paper first implements unsupervised classification of financial transaction data based on Support Vector Machines, which automatically classifies the data into normal and abnormal categories.Histograms are introduced in combination with LightGBM to quickly fuse data from multiple sources.The most suitable first layer is selected by different algorithms, and the outputs of these algorithms are combined with industry-wide common abnormal features as inputs for LightGBM's second layer identification.With this two-layer structure, the model not only takes into account the industry characteristics, but also the common anomaly features.Empirical results show that in the accuracy of smart financial statement generation, the sensitivity of this paper's model iterates to 99.99% at 41.25% specificity, and the accuracy of this paper's model is as high as 0.98 when dealing with financial private information, macroeconomic, and market information.In the identification of financial transaction anomalies, the number of anomalous weeks is identified to be 24, 29, 34, and 36, and the fusion of multi-source data effectively identifies the large amount of financial transactions, fluctuating transactions and other suspicious abnormal transactions.
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.
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 | 0.009 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 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 it