Supply chain fraud prediction with machine learning and artificial intelligence
Bibliographic record
Abstract
As businesses undergo digital transformation, supply chain fraud poses an increasing threat, necessitating more sophisticated detection and prevention methods. This paper explores the application of machine learning (ML) and artificial intelligence (AI) in detecting and preventing supply chain fraud. The research design involves analyzing a dataset of supply chain operations and employing various ML algorithms to detect consumer-based fraud within the supply chain, which occurs when consumers partake in deceptive practices during the order process of e-commerce transactions. We analyzed 180,000 transactions from an international company recorded between 2015 and 2018. This study emphasises the necessity of human oversight in interpreting the results generated by these technologies. The implications of supply chain fraud on financial stability, legal standing, and reputation are discussed, along with the potential for ML technology to identify irregularities indicative of fraud. Descriptive findings highlight the prevalence of fraudulent transactions in specific payment types. The AI sequential and the CatBoost classifiers were the top-performing algorithms across all performance metrics. The top features to detect unusual orders are delivery status, payment type, and late delivery risks. The discussion emphasises the promising predictive capabilities of the ML and AI models and their implications for detecting supply chain fraud.
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 | 0.008 | 0.022 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.008 | 0.006 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.001 | 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".