Self-checkout terminal event and loss-prevention dataset

Name: Self-checkout terminal event and loss-prevention dataset: per-transaction intervention and anomaly events at SCO lanes (skip-scans, produce and bakery PLU weigh mismatches where a premium item is keyed as a cheaper code), weighed-item versus keyed-PLU pairs, attendant intervention rates, and per-store net-efficiency metrics reconciling labor hours displaced against incremental shrink applied to SCO sales; adjacent store-level grocery price and promotion optimization data
Creator: Ward (GetWard)

WARD (GETWARD)Manage supplier listing

Self-checkout terminal event and loss-prevention dataset: per-transaction intervention and anomaly events at SCO lanes (skip-scans, produce and bakery PLU weigh mismatches where a premium item is keyed as a cheaper code), weighed-item versus keyed-PLU pairs, attendant intervention rates, and per-store net-efficiency metrics reconciling labor hours displaced against incremental shrink applied to SCO sales; adjacent store-level grocery price and promotion optimization data

Open buyer room →

Sample

Brickroad customers

Sample this dataset before you buy it.

Your sourcing agent asks Ward (GetWard) and files the sample in your catalog — private to you.

Start 7-day trialNothing is charged until the trial ends.

Coverage

Universe, instruments and categories.

Industry: Application SoftwareFood Retail
Instruments: equities
Categories: AlternativeSentimentSupply Chain
Regions: US
Sample tickers: KRACIWMTCOSTSBSIGAPTPEPPGTSNHRL

Dataset card

Type: not stated
Format: Tabular event and transaction records (lane, terminal, timestamp, item or PLU, intervention outcome, attendant action) joined to store-level labor and shrink aggregates, delivered as per-store dashboards and rankings
Volume: Bounded by pilot scale - estimate order 10-500 stores under monitoring, which at typical self-checkout volumes means order 1-50 million SCO transactions monitored per year with an intervention or exception rate of roughly 1-5 percent, so order 100K-2M labeled anomaly events per year
Users: N/A - a two-person startup with no published customer or account count; likely a small pilot-scale grocery customer base
History: not stated
Update frequency: not stated
Growth: Active but very early (two-person team, no disclosed funding, an actively published technical blog and multiple distinct grocery product pages covering shrinkage detection and price optimization)
Launched: ~2025-2026 (inferred: the provider company record for getward.ai was created in 2026 and the company has no disclosed funding history or earlier press)
Delivery: not stated
Entity mapping: not stated
Sample: not stated
Point-in-time: not stated
Licence: not stated

supplier index read from their site

Ward (GetWard) has not added their own details yet. Not yet on file:

Dataset
Data dictionary
Coverage
Provenance
Rights & data handling