Typology analyzers
Card, account-to-account, statement, credit, merchant, account takeover and document analyzers. Every signal has a code, a weight and a typology it points to.
A decision model for fraud, AML, compliance and risk. It takes a case and returns APPROVE, STEP_UP or DECLINE with a probability for each risk line, the signals behind it and what it could not check. It does not generate text.
Fraud, AML and sanctions are answered separately, so a sanctions stop is never mistaken for a fraud score. Each line states its probability, its interval and how it was calibrated.
{
"model": "ward-1",
"decision": "DECLINE",
"outcome": { "choice": { "DECLINE": 0.58, "STEP_UP": 0.42 },
"confidence": 0.37 },
"risks": {
"fraud": { "p": 0.598, "interval": [0.40, 0.87],
"calibration": "reference_calibrated" },
"aml": { "level": "escalate", "gates": false },
"sanctions": { "status": "clear" }
},
"initiator": "cardholder",
"signals": [ … ],
"needs": [ … ],
"not_assessed": [ … ]
}
Field reference in the docs.
Raw scores are mapped to probabilities with a reference map and shifted to your base rate. A line is labelled reference_calibrated only when its held-out calibration error is 0.05 or less.
| Reference map | Blocks | Held-out ECE | AUC | Status |
|---|---|---|---|---|
| Card fraud | 10 | 0.0104 | 0.877 | REFERENCE CALIBRATED |
| Statement AML | 14 | 0.0392 | 0.897 | REFERENCE CALIBRATED |
Lines are refitted on each client's own labelled outcomes as they arrive. Set your base rate per client.
Two ISO 8583 suites: one where the cardholder has 25 to 50 past transactions, and a cold set with a profile and no usable history. Fraud stopped is measured at a 5% false-decline budget.
| Suite | Scorer | AUC | Fraud stopped at 5% false declines | Genuine approved at 0.5 | Tokens / call |
|---|---|---|---|---|---|
| With history | Ward | 0.983 | 89 of 101 | 298 of 298 | 113 |
| Cold start | Ward, with profile | 0.952 | 55 of 65 | 228 of 229 | 238 |
ISO 8583 card authorization benchmarks, October 2026.
Ward is not one opaque network. Each decision type has its own analyzer whose signals and weights are documented. Learned layers are added on top only when they beat the analyzer on later cases.
Card, account-to-account, statement, credit, merchant, account takeover and document analyzers. Every signal has a code, a weight and a typology it points to.
OFAC, UN, UK and EU sanctions lists, PEP and enforcement records, adverse media, and WMID, Ward's merchant intelligence data.
Seven decision gates and two system steps, the KYA Score and the six EDQS-B behavioral detectors, for payments started by AI agents.
Isotonic maps with intervals and a base-rate shift turn raw scores into probabilities you can set thresholds on.
Scorecards and boosted trees trained on your labelled outcomes. They run in shadow, show their reasons and cut points, and decide only after maker-checker approval.
A learned column reader for files in any layout and seven languages, MRZ and document forensics, and ISO 8583 data elements for card exports.
GET /api/v1/models lists the served release, its components and the change log. Pin a version for stability or follow ward-1.
POST /api/v1/decide for payment, intent, agent, screen, document and statement; then account takeover, credit and merchant types, async jobs and the governance pack.