Catalog record · Fraud Detection & AML
Stage as of source date not established · historical report, not live reconfirmation.
Custom ML screening of gift-card transactions to prevent chargeback fraud
Vendor workflow source. A reviewed supplier account names the customer and workflow. Supplier attribution and deployment claims are not independent outcome validation.
Last researched Oct 29, 2026. Source access and reported stage are recorded below; deployment evidence does not establish ROI.
What the research supports
Raise uses Sardine custom ML models together with tuned rules to detect gift-card fraud. The vendor/customer case reports chargebacks falling from 0.53% to 0.29% and manual reviews from 15–18% to 0.25% of transactions.
- Reported stage
- Production
- Technology
- Machine Learning
- Business function
- Not assessed
- Impact (legacy label)
- Not labeled
- Catalog date · unconfirmed
- Not reported
- Imported
- Oct 29, 2026
- Last researched
- Oct 29, 2026
Measures & evidence
No quantified measure recorded. This is a gap in the evidence, not a finding of no value.
Documented vendor relationships
No vendor relationship has been linked to this specific workflow in the curated overlay. This does not mean it was built without vendors.
See the company’s documented relationshipsDeployment evidence & limits
Production — undated customer case accessed 2026-10-29; older story resurfaced in 2026-10-27 coverage Status date not established.
Stage is as reported in the cited evidence. Current operating status has not been independently reconfirmed; the research date is an editorial review date.
October 27, 2026 is the secondary article date, not a new deployment date. Source describes a three-year partnership without an absolute measurement period. Marketplace case; this is prevention, not dispute-evidence preparation. Metrics combine ML, rules and workflow changes; no causal ML-only attribution.
Potential FS application · inferred
Merchant/acquirer risk screening for stored-value marketplaces.
Merchant/acquirer risk screening for stored-value marketplaces.
Original industry: Gift-card marketplace. Transfer limits: Marketplace case; this is prevention, not dispute-evidence preparation. Metrics combine ML, rules and workflow changes; no causal ML-only attribution.
Source register
- How Raise reduced chargebacks and manual reviews with Sardinesardine.ai · opens in a new tab
Sardine · vendor-case · full-text · Publication date not recorded
- How Raise reduced chargebacks and manual reviews with Sardine (Japanese edition)sardine.ai · opens in a new tab
Sardine · vendor-case · indexed-primary · Published 2025-03-07
- Raise Cuts Chargebacks 45% and Nearly Ends Manual Fraud Reviewspymnts.com · opens in a new tab
PYMNTS · news · blocked · Published 2026-10-27
Research lanes: payments_treasury · Batch global-discovery-2026-10-29. Coverage and remaining gaps