AI Insights Module · Governance
Bias & Fairness Monitor
AI Generated Fairness Summary
AI analyzed outcome distributions across 247 production models spanning 18.4 million predictions today. Churn Prediction v3.2 shows a 6.2 point risk-score disparity between SMB and Enterprise accounts — within acceptable variance and explained by contract tenure. Fraud Detection v4.1 was flagged for review after its false-positive rate diverged 11.4 points for accounts in the APAC region versus the global baseline, with no legitimate risk factor identified yet. Recommendation: recalibrate Fraud Detection v4.1's regional threshold and re-run parity validation within 5 business days.
Explain This Fairness Summary
Model
Fairness Parity Auditor v1.6 (statistical parity & disparate-impact scan over 6 production models)
Data Sources
Churn Prediction v3.2 and Fraud Detection v4.1 outcome logs, segmented by account tier and region, covering the trailing 30-day window.
Why 94.1% confidence
Disparity measurements were computed across 30 daily snapshots with a stable trend; the 6.2 point Churn gap is fully attributable to contract tenure differences, while the Fraud Detection gap lacks a confirmed legitimate driver, lowering overall confidence.
Suggested Action Rationale
Regional threshold recalibration for Fraud Detection v4.1 is prioritized because APAC false-positive rates directly translate into blocked legitimate transactions, carrying the largest quantified business exposure of the flagged items.
Fairness Score by Model
Composite parity score (0–100) across all monitored business-segment outcome checks
Churn Prediction v3.2
91
FairRevenue Forecasting v2.7
88
FairFraud Detection v4.1
61
FlaggedCustomer Segmentation v1.9
76
Needs ReviewDemand Planning v2.3
93
FairSentiment Analysis v1.4
85
FairParity Metric Comparison
Higher = more consistentFive parity dimensions scored 0–100 across three production models
Segment Parity Breakdown
Outcome metrics by business segment — Fraud Detection v4.1
| Business Segment | Accounts | Avg Risk Score | Approval Rate | False Positive Rate | Parity Delta |
|---|---|---|---|---|---|
| SMB | 14,820 | 42.1 | 91.4% | 3.8% | Baseline |
| Mid-Market | 6,340 | 44.6 | 89.9% | 4.5% | +0.7 pt |
| Enterprise | 2,110 | 46.9 | 88.2% | 7.2% | +3.4 pt |
| APAC region | 5,280 | 51.3 | 84.6% | 15.2% | +11.4 pt |
What's Driving the Fraud Detection v4.1 Disparity
The 11.4 point false-positive rate gap for APAC-region accounts is not explained by transaction volume, account age, or declared risk category — the three legitimate factors the model is permitted to weight. Cross-referencing device-fingerprint diversity and payment-method mix (both correlated with but not equivalent to region) accounts for roughly 4 of the 11.4 points. The remaining 7.4 points show no confirmed legitimate driver and are consistent with a regional data-drift issue introduced when the APAC transaction gateway was migrated eight weeks ago. Recommendation: hold the APAC threshold at the pre-migration calibration until a re-fit completes.
Active Fairness Reviews
Fraud Detection v4.1 — APAC false-positive rate disparity (+11.4 pt)
Assigned to Marcus Lee · Opened 2 days ago
Customer Segmentation v1.9 — tenure-band recommendation skew
Assigned to Priya Patel · Opened 5 days ago
Revenue Forecasting v2.7 — industry-vertical variance under monitoring
Assigned to Sarah Chen · Opened 1 day ago
Fairness thresholds and business-segment definitions are reviewed quarterly by the AI Governance Council.