The Future of AI-Powered Auditing: Enhancing Accuracy and Reducing Errors
Bibliographic record
Abstract
The adoption of artificial intelligence (AI) technologies is significantly improving monitoring functions while also transforming audit functions by providing increased precision, audit scalability, and real-time monitoring capabilities. In this paper, we propose an audit methodology based on artificial intelligence (AI) that incorporates the processes of data gathering, data cleansing, machine learning application, and anomaly detection to streamline error-prone audit processes and increase audit accuracy. A multi-stage model was built and tested in five industry sectors, and the model demonstrated better performance in anomaly detection and audit efficiency in all the sectors tested. The AI technologies have proven, using a novel-designed Audit Enhancement Index (AEI), to have substantially more efficiency in comparison to the traditional methods of auditing in a data-rich industry. An additional detailed workflow diagram and summary chart have been provided to visually demonstrate the advantages of the system over the traditional methods. AI can redefine the auditing processes from a post hoc examination of information to an ongoing, intelligent reevaluation of real-time data streams. This research has the potential to significantly advance automation in auditing and change perceptions of auditors to vision strategists empowered by instantaneous AI data analysis.
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 | 0.012 | 0.029 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.007 | 0.009 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".