# Provenance Impact Report

- Run ID: `20260807T053217Z-544a48`
- State: **PUBLISHED**
- Started: 2026-08-07 05:32:17.105619+00:00
- Completed: 2026-08-07 05:32:23.296966+00:00

## Proposed Change

- Asset: `urn:li:dataset:(urn:li:dataPlatform:kafka,payments.authorized_transaction_events,PROD)`
- Source column: `transactions_last_10_minutes`
- Scenario: transaction-velocity-surge
- Request: A payment-fraud monitoring agent detected a sixfold transaction-velocity surge across eight percent of evaluated payments, consistent with an account-takeover-shaped stress condition.
- Trigger event: `account-takeover-001`
- Trigger source: `payment-fraud-monitoring-agent`

## DataHub Context (through MCP)

- Source: `urn:li:dataset:(urn:li:dataPlatform:kafka,payments.authorized_transaction_events,PROD)` (payments.authorized_transaction_events)
- Selected field: `transactions_last_10_minutes`
- Owners: `urn:li:corpGroup:payment-fraud-monitoring`
- Tags: Production, PaymentFraud, RealTimeML

### Complete lineage

| Hop | Upstream | Downstream | Relationship |
| ---: | --- | --- | --- |
| 1 | `urn:li:dataset:(urn:li:dataPlatform:kafka,payments.authorized_transaction_events,PROD)` | `urn:li:dataset:(urn:li:dataPlatform:postgres,fraud.realtime_payment_features,PROD)` | lineage |
| 2 | `urn:li:dataset:(urn:li:dataPlatform:postgres,fraud.realtime_payment_features,PROD)` | `urn:li:mlFeature:(realtime_payment_risk_features,transactions_last_10_minutes)` | lineage |
| 3 | `urn:li:mlFeature:(realtime_payment_risk_features,transactions_last_10_minutes)` | `urn:li:mlModel:(urn:li:dataPlatform:mlflow,payment_fraud_detector_v3,PROD)` | lineage |

### Affected models

- `urn:li:mlModel:(urn:li:dataPlatform:mlflow,payment_fraud_detector_v3,PROD)` ➔ payment_fraud_detector_v3

### Evidence URNs

- `urn:li:dataset:(urn:li:dataPlatform:kafka,payments.authorized_transaction_events,PROD)`
- `urn:li:dataset:(urn:li:dataPlatform:postgres,fraud.realtime_payment_features,PROD)`
- `urn:li:mlFeature:(realtime_payment_risk_features,transactions_last_10_minutes)`
- `urn:li:mlModel:(urn:li:dataPlatform:mlflow,payment_fraud_detector_v3,PROD)`

## Experiment Plan

- Target asset: `urn:li:dataset:(urn:li:dataPlatform:kafka,payments.authorized_transaction_events,PROD)`
- Rationale Explanation: **_Reproduce the observed account-takeover-shaped velocity surge against a bounded evaluation cohort and measure how the affected fraud model behaves._**
- Expected signals: AUC drop, prediction flip rate, mean absolute probability shift

| # | Operator | Column | Fraction | Value |
| ---: | --- | --- | ---: | --- |
| 1 | `scale_numeric` | `transactions_last_10_minutes` | 0.08 | 6.0 |

## Observed Results

### Experiment 1: `scale_numeric`

- Column: `transactions_last_10_minutes`
- Duration (_how long the mutation and mutated inference took_)[ms]: 5.49460000002
- Error: n/a

| Metric | Observed value |
| --- | ---: |
| `baseline_auc` | 0.8092934782608696 |
| `mutated_auc` | 0.7688586956521739 |
| `auc_drop` | 0.04043478260869571 |
| `prediction_flip_rate` | 0.038 |
| `mean_absolute_probability_shift` | 0.038155929963187674 |
| `inference_error_rate` | 0.0 |

- Rows selected: 40 / 500
- Before summary: `{"maximum": 6.0, "mean": 1.806, "minimum": 0.0, "missing": 0}`
- After summary: `{"maximum": 24.0, "mean": 2.436, "minimum": 0.0, "missing": 0}`

## Deterministic Decision

- Status: **WARN**
- Summary: Warning triggered by 1 deterministic rule(s).

### Triggered policy rules

| Experiment | Metric | Observed | Rule | Result | Reason |
| ---: | --- | ---: | --- | --- | --- |
| 1 | `auc_drop` | 0.04043478260869571 | >= 0.02 | WARN | AUC drop 0.040435 reached warning threshold 0.020000 |

## Publication

- Local JSON: `mockup_data/artifacts/runs/20260807T053217Z-544a48.json`
- Local Markdown: `mockup_data/artifacts/runs/20260807T053217Z-544a48.md`
- Remote succeeded: yes
- DataHub tag: Provenance-WARN
- DataHub document: urn:li:document:shared-4c6c03c6-335b-4271-9930-228ca658b570
- Remote error: n/a