Transforming Tax Compliance with Machine Learning: Reducing Fraud and Enhancing Revenue Collection
Bibliographic record
Abstract
The integration of machine learning (ML) in tax administration has the potential to revolutionize tax compliance, enhancing fraud detection and optimizing revenue collection. This literature review explores the application of ML in tax systems, emphasizing its transformative role in addressing the limitations of traditional, labor-intensive compliance methods. Justification for adopting a literature review approach is rooted in the need to consolidate diverse perspectives, address research gaps, and provide an informed synthesis of existing findings. The study highlights the criteria used for selecting case studies and research papers, ensuring a robust analysis of ML’s ability to automate detection processes, improve risk assessment, and enable predictive analytics for efficient tax administration. Despite its potential, ML adoption is challenged by data quality issues, privacy concerns, technical infrastructure demands, and ethical considerations, which must be systematically addressed. This paper also identifies literature gaps, particularly the lack of balanced discourse, and provides recommendations for overcoming barriers, including enhancing data management practices, adopting ethical frameworks, and fostering cross-border collaboration. By addressing these challenges, ML can equip tax authorities with tools for creating efficient, adaptive, and fair systems. This research underscores ML’s growing importance in transforming global tax compliance, setting the stage for a future of more responsive and effective revenue administration.
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 | 0.026 | 0.083 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.007 |
| Science and technology studies | 0.002 | 0.004 |
| Scholarly communication | 0.010 | 0.011 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 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".