Signals for review only: Flags reflect statistical and rule-based anomalies worth reviewing — never confirmed fraud. CSV import only; customer emails are salted-hashed.

Signal Triage Ledger

Flagged Anomalies (18)

Every flag is a statistical or rule-based signal worth reviewing — filter, bulk-mark decisions, or open any row for AI explanation and linked transactions.

Severity / ScoreRuleSignal & ExplanationStatusAction
highScore 98/100
Duplicate

3 row(s)

Possible duplicate refund on charge ch_demo_dup_001 (+$189.00 over charge)

2 refunds totaling $378.00 reference charge ch_demo_dup_001 (original charge $189.00). Combined refunds exceed the charge by $189.00 — worth reviewing for duplicate refund processing.

OpenInspect
highScore 98/100
Duplicate

3 row(s)

Possible duplicate refund on charge ch_demo_dup_002 (+$329.00 over charge)

2 refunds totaling $658.00 reference charge ch_demo_dup_002 (original charge $329.00). Combined refunds exceed the charge by $329.00 — worth reviewing for duplicate refund processing.

OpenInspect
highScore 97/100
Over-Refund

2 row(s)

Refund re_demo_over_001 exceeds original charge ch_demo_over_001 by $124.00

Refund re_demo_over_001 for $248.00 is larger than original charge ch_demo_over_001 ($124.00) — an overage of $124.00. Worth reviewing for data-entry error, currency mismatch, or unauthorized credit.

OpenInspect
highScore 94/100
Velocity

5 row(s)

Customer refund velocity outlier: r***@example.com · #d917b629 (5 refunds, $800.00)

Customer r***@example.com · #d917b629 accumulated 5 refunds totaling $800.00, exceeding the cohort 3σ threshold of 2.9 refunds (mean 0.39, σ=0.83). Worth reviewing account history and support tickets.

OpenInspect
highScore 94/100
Velocity

7 row(s)

Customer refund velocity outlier: v***@example.com · #af39114a (7 refunds, $579.95)

Customer v***@example.com · #af39114a accumulated 7 refunds totaling $579.95, exceeding the cohort 3σ threshold of 2.9 refunds (mean 0.39, σ=0.83). Worth reviewing account history and support tickets.

OpenInspect
highScore 92/100
High Ratio

6 row(s)

High refund ratio for r***@example.com · #97b249e3 (100% of 3 charges)

Customer r***@example.com · #97b249e3 has 3 refunds across 3 charges (100% by count; $175.05 refunded of $175.05 charged, 100% by value), exceeding the 50% review threshold. Worth reviewing for product-fit issues, fulfillment errors, or policy abuse.

OpenInspect
highScore 92/100
High Ratio

14 row(s)

High refund ratio for v***@example.com · #af39114a (100% of 7 charges)

Customer v***@example.com · #af39114a has 7 refunds across 7 charges (100% by count; $579.95 refunded of $579.95 charged, 100% by value), exceeding the 50% review threshold. Worth reviewing for product-fit issues, fulfillment errors, or policy abuse.

OpenInspect
highScore 92/100
Velocity

16 row(s)

Daily refund velocity spike on 2026-11-12 (16 refunds, $1,547.60)

2026-11-12 recorded 16 refunds totaling $1,547.60 compared to a daily baseline of 2.5 refunds (σ=2.8, 3σ threshold=10.9) and $226.83/day. This statistical outlier is worth reviewing for an incident, batch error, or coordinated return wave.

OpenInspect
highScore 91/100
Over-Refund

3 row(s)

Cumulative refunds on ch_demo_dup_001 exceed charge by $189.00

2 refunds linked to charge ch_demo_dup_001 total $378.00, exceeding the original charge of $189.00 by $189.00. Worth reviewing in your Stripe dashboard.

OpenInspect
highScore 91/100
Over-Refund

3 row(s)

Cumulative refunds on ch_demo_dup_002 exceed charge by $329.00

2 refunds linked to charge ch_demo_dup_002 total $658.00, exceeding the original charge of $329.00 by $329.00. Worth reviewing in your Stripe dashboard.

OpenInspect
highScore 88/100
Card Mismatch

2 row(s)

Possible card fingerprint mismatch on refund re_demo_fpm_1

Refund re_demo_fpm_1 ($134.50) recorded card fingerprint "fp_demo_diff_card_1", whereas original charge ch_demo_fpm_1 used "fp_demo_orig_card_1". While card re-issuance or network token updates can occasionally change fingerprints, this mismatch is worth reviewing.

OpenInspect
highScore 88/100
Card Mismatch

2 row(s)

Possible card fingerprint mismatch on refund re_demo_fpm_2

Refund re_demo_fpm_2 ($176.75) recorded card fingerprint "fp_demo_diff_card_2", whereas original charge ch_demo_fpm_2 used "fp_demo_orig_card_2". While card re-issuance or network token updates can occasionally change fingerprints, this mismatch is worth reviewing.

OpenInspect
highScore 88/100
Card Mismatch

2 row(s)

Possible card fingerprint mismatch on refund re_demo_fpm_3

Refund re_demo_fpm_3 ($219.00) recorded card fingerprint "fp_demo_diff_card_3", whereas original charge ch_demo_fpm_3 used "fp_demo_orig_card_3". While card re-issuance or network token updates can occasionally change fingerprints, this mismatch is worth reviewing.

OpenInspect
mediumScore 86/100
Velocity

4 row(s)

Customer refund velocity outlier: r***@example.com · #f1863b43 (4 refunds, $388.50)

Customer r***@example.com · #f1863b43 accumulated 4 refunds totaling $388.50, exceeding the cohort 3σ threshold of 2.9 refunds (mean 0.39, σ=0.83). Worth reviewing account history and support tickets.

OpenInspect
highScore 85/100
High Ratio

9 row(s)

High refund ratio for r***@example.com · #f1863b43 (80% of 5 charges)

Customer r***@example.com · #f1863b43 has 4 refunds across 5 charges (80% by count; $388.50 refunded of $508.50 charged, 76% by value), exceeding the 50% review threshold. Worth reviewing for product-fit issues, fulfillment errors, or policy abuse.

OpenInspect
highScore 82/100
Rapid (<10m)

6 row(s)

Rapid charge → refund pattern for r***@example.com · #97b249e3 (3 pairs under 10m)

Customer r***@example.com · #97b249e3 had 3 charges refunded within 10 minutes of creation (fastest: 2m 15s, total $175.05). Rapid charge-then-refund cycles can indicate checkout retry bugs, card testing, or operator reversals and are worth reviewing.

OpenInspect
mediumScore 74/100
Duplicate

2 row(s)

Possible duplicate $74.50 refund to s***@example.com · #092bb082 within 3.8 hrs

2 identical refunds of $74.50 (total $149.00) were issued to s***@example.com · #092bb082 within 3.8 hrs. Identical same-day refund amounts may indicate an accidental retry and are worth reviewing.

OpenInspect
mediumScore 74/100
Round Cluster

5 row(s)

Round-amount refund cluster for r***@example.com · #d917b629 (5 refunds, $800.00)

5 exact round-dollar refunds ($100.00, $200.00, $150.00, $250.00) totaling $800.00 were issued to r***@example.com · #d917b629. Repeated round-number manual credits are worth reviewing to confirm they align with documented goodwill or SLA adjustments.

Note: Confirmed with support: scheduled SLA goodwill credits for Q4 maintenance window.

Reviewed — OKInspect
Flagged Signals · RefundRadar