Feedback Loop
Submit analyst labels and use them as supervised learning input for future Sentra models.
Sentra improves through feedback. Analyst outcomes and partner labels are stored as feedback_labels and converted into a fraud target during training.
Submit feedback
curl "$SENTRA_API_BASE/v1/risk/feedback" \
-H "Authorization: Bearer $SENTRA_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"tx_id": "m2txn_260605_001",
"label_type": "fraud",
"label_value": 1,
"source": "manual",
"note": "Analyst confirmed account takeover pattern.",
"labeled_at": "2026-06-05T12:30:00Z"
}'Required role: Analyst or Admin.
Accepted labels
| Label type | Meaning | Training target |
|---|---|---|
fraud | Confirmed fraud outcome. | Positive when label_value=1, negative when 0. |
chargeback | Chargeback-confirmed loss event. | Positive when 1, negative when 0. |
blocked | Confirmed block-worthy event. | Positive when 1, negative when 0. |
false_positive | Analyst confirmed the transaction was safe. | Negative when 1; 0 is stored but ignored. |
refund | Operational refund outcome. | Stored, ignored for fraud target. |
other | Catch-all operational note. | Stored, ignored for fraud target. |
Accepted sources:
manualsystempartner
Training target resolution
During training:
- Any positive target wins.
- If no positive target exists but a negative target exists, the transaction is negative.
- Ignored labels remain available for history but do not affect the fraud model target.
Console workflow
- Analyst opens
/cases/{case_id}. - Analyst reviews transaction context, score, reasons, evidence, AI status, and history.
- Analyst updates notes, status, and final decision.
- Analyst submits feedback label.
- Feedback appears in case history.
- Future model training reads feedback labels from the dataset or DB.
What feedback does not do
POST /v1/risk/feedback does not trigger training immediately. Training is a controlled Admin/model-ops action so the team can review data quality, label coverage, metrics, and model provenance before activation.
Recommended label policy
Before production learning, define:
- What counts as confirmed fraud.
- What counts as false positive.
- Whether chargebacks are always fraud-positive.
- Which system outcomes are trusted enough for
source=system. - Whether compliance decisions should be
blocked,fraud, orother. - How long to wait before converting open reviews into training labels.