Handling Concept Drift in Fraud Detection: A Replication Study
Bibliographic record
Abstract
Fraud detection is becoming more important in environments where data patterns change over time. This makes it necessary to adjust detection systems to keep up with new fraud strategies. The main motivation of this study is to replicate and extend the study of \cite{dal2015credit}, which proposed novel approaches to address concept drift in fraud detection within real-world settings. The original study used proprietary datasets. We conducted the replication study using two open access datasets. We extended the replication study by a) comparing the algorithms in the original study with an algorithm used in another study; and b) with algorithms that do not account for concept drift. Some of our results align with the original study, while others differ. For example, we found consistent results with the original study that treating delayed feedbacks separately from immediate feedback leads to higher recall rates in fraud detection. On the other hand, we found that some simple methods for dealing with concept drift may give the same or even better results than more complex methods.
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 | 0.143 | 0.438 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.005 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.005 | 0.009 |
| Open science | 0.005 | 0.003 |
| Research integrity | 0.004 | 0.005 |
| 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".