Loss Prevention · All retail

Sweethearting Detection

Discount and void patterns suggest sweethearting. Correlates operator and lane.

Target KPI Shrink
Executes in ≤ 48 hours
System of record POS · LP analytics
Trigger condition

Employee-discount, manual-override or skip-scan indicators concentrate on an operator well outside the peer distribution, and repeat across shifts.

Write-back

Review case opened in LP analytics with the signal set and peer comparison attached; observation scheduled.

Every write is gated on an approver role you name. Nothing runs unattended.

Procedure
  1. Combine the weak signals, since no single one is evidence: scan gaps, discount frequency, and basket value against lane norms.
  2. Test whether the pattern follows the operator across lanes and shifts, which separates behaviour from equipment.
  3. Check the mundane explanations: a faulty scanner, a produce code everyone gets wrong, an untrained new starter.
  4. Route to LP as a review with the statistical basis stated plainly, so a human judges it rather than a threshold.
  5. Close when the pattern resolves, whether through coaching, a repair, or a substantiated case.
Outcome metric

Signal concentration against the peer distribution over 45 days, and recovered value where substantiated.

The case closes on this number, not on the action being taken. A playbook without a close condition is a dashboard.

Run Sweethearting Detection on your data.

Pick three playbooks from the catalog. We wire them against your system of record for the pilot.

Read-only to start · your LLM keys · SOC 2 Type II underway · or book a call directly

Find out what your data has been hiding.

Tell us about your operation. We’ll show you the problems Ward catches, and the ones your current tools miss.

Step 1 of 3
What are your goals?
Step 2 of 3
About your operation
Step 3 of 3
Your contact info