Detecting anomalies in financial statements using machine learning algorithm
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
Purpose The purpose of this paper is to evaluate the possibility of rating the credit worthiness of a firm’s quarterly financial report using a dynamic anomaly detection method. Design/methodology/approach The study uses a data set containing financial statements from Quarter 1 – 2001 to Quarter 4 – 2016 of 937 Vietnamese listed firms. In sum, 24 fundamental financial indices are chosen as control variables. The study employs the Mahalanobis distance to measure the proximity of each data point from the centroid of the distribution to point out the extent of the anomaly. Findings The finding shows that the model is capable of ranking quarterly financial reports in terms of credit worthiness. The execution of the model on all observations also revealed that most financial statements of Vietnamese listed firms are trustworthy, while almost a quarter of them are highly anomalous and questionable. Research limitations/implications The study faces several limitations, including the availability of genuine accounting data from stock exchanges, the strong assumptions of a simple statistical distribution, the restricted timeframe of financial data and the sensitivity of the thresholds for anomaly levels. Practical implications The study opens an avenue for ordinary users of financial information to process the data and question the validity of the numbers presented by listed firms. Furthermore, if fraud information is available, similar research can be conducted to examine the tendency for companies with anomalous financial reports to commit fraud. Originality/value This is the first paper of its kind that attempts to build an anomaly detection model for Vietnamese listed companies.
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 | 0.004 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.000 | 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