Bibliographic record
Abstract
Abstract The incidence of consumer credit card fraud has been on the increase worldwide over the past 2 years. In Canada alone. the cost of credit card fraud totaled (for Visa and Master card) more than 46 million Canadian dollars for 1991. This number compares to totals of about $29 million for 1990 and only $19 million for 1989 (Appleby 1992). The two predominant growth areas are that of counterfeit fraud (where an unauthorized duplicate of the card exists in circulation) and that of non-receipt fraud (where a re-issued card is intercepted by a third party). In both instances. the cardholder is unaware that a copy of his or her card is in the hands of criminals and hence. the fraud is not reported. Consequently, the amount of financial exposure for the financial institution is substantially higher than that for a lost or stolen card, for example, where the cardholder is aware almost immediately. The lost or stolen card is usually reported within the first day to the issuing company and a block is placed on that account. thereby limiting spending. The objective of this chapter is to construct and implement a rule-based. expert system model to detect the fraudulent usage of credit before the fraud activity has been reported by the cardholder. If this can be accomplished, the credit granting institution will NOT have to rely on the cardholder to report the fraudulent activity. In the case of counterfeit fraud. for example. this can take a substantial number of days-on average, 8-10 days according to bank statistics. The methodology is as follows. Suspicious activity can be detected from deviations from ‘normal ‘ spending patterns through the use of expert systems. As a result. the customer can be contacted and the account blocked (if so warranted--all within the first few hours of the 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 | 0.001 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".