SCARFF : A scalable framework for streaming credit card fraud detection with spark¶
Carcillo. (2018). SCARFF : A scalable framework for streaming credit card fraud detection with spark.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Domain-specific¶
- Stream Processing
- When a card is swiped, the authorization event flows into a streaming engine (commonly Kafka feeding Flink or a similar stateful processor), which scores the transaction against a rolling per-card behavioral window — recent spend, merchant categories, geographic velocity — and must return an approve/decline signal within milliseconds, before the point-of-sale terminal times out.
This sourceProduction credit-card fraud-detection framework in which Kafka carries transactions into Spark Streaming, which scores them online against per-cardholder historical feature windows in near-real-time.
Supported in partVerified against the work's full text
“Apache Kafka3 is a distributed publish-subscribe messaging queue system that is commonly used for log collection.”
- When a card is swiped, the authorization event flows into a streaming engine (commonly Kafka feeding Flink or a similar stateful processor), which scores the transaction against a rolling per-card behavioral window — recent spend, merchant categories, geographic velocity — and must return an approve/decline signal within milliseconds, before the point-of-sale terminal times out.
Verification¶
Does it exist? Not checked yet. This work's DOI is recorded above but has not been resolved against an external catalogue, so nothing here confirms the work exists.
Does it back the claim? Read against the text for 1 of 1 citation: 1 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:6f7254dcb4e9 · see in the full table