Shrinkage Detection: Grocery retail, BigQuery data, Supply Chain decisions
Ward reads any BigQuery dataset, gA4 event exports, ads data transfers from Google BigQuery, watches shrinkage across 30,000+ grocery SKUs, and sends the supply chain read on a daily cycle.
How a grocery VP Supply Chain runs shrinkage on Google BigQuery
You find out about stockouts after customers do. Ward surfaces the indicators that change a supply chain decision.
What shrinkage detection does: Ward identifies abnormal inventory loss patterns and distinguishes between theft, damage, spoilage, and administrative error.
Applied to Grocery & Supermarket, the surface area is 30,000+ SKUs throughout stores. Fresh availability, shrinkage, and promo effectiveness across hundreds of stores. Ward monitors perishable turn rates and flags waste before it happens.
How Ward hands back Shrinkage cards: Ward compares expected inventory against actual counts, segments loss by cause category, and flags store-level anomalies against your estate baseline.
How the connection works. Service account with BigQuery Data Viewer role. Ward runs read-only SQL queries on your schedule.
Capabilities
- Pattern recognition across time
- Cause-level shrinkage attribution
- Store-vs-estate benchmarking
- Receiving dock anomaly detection
Chat
Ask anything. Ward routes to the right agent and returns cited answers.
I pulled Store 37’s last 28 days against the chain baseline. Two root causes, both compounding.
| Signal | Finding |
|---|---|
labor_efficiency | Rev/labor-hour −22% vs. cluster, staffing mismatch at 11a–1p peak |
inventory.fresh | Fresh fill 83%, backroom replenishment lag at 2–4p |
promo.lift | BOGO crackers cannibalized Brand Y by 28%, net category +6% |
Recommend: re-baseline Store 37 schedule against true peak, raise replen window to 1p, and review the BOGO before next cycle.
labor_scheduling…
Reporting
Pinned views built from saved data-lake queries. Every number re-derivable from its SQL.
| Model | Horizon | MAPE |
|---|---|---|
holt_winters | 4wk | 4.1% |
arima_sarimax | 13wk | 8.9% |
gbm_demand | 1wk | 2.1% |
bayes_hier | new store | 11.4% |
Sources
Connect external systems to the data lake.
| Name | Type | Last sync |
|---|---|---|
sap_pos_transactions | import | 2m ago |
sap_inventory_shrinkage | import | 2m ago |
sap_labor_scheduling | import | 14m ago |
relex_replenishment_plan | import | 1h ago |
blue_yonder_forecast_daily | import | 1h ago |
retail_fresh_waste_daily | import | 1h ago |
retail_promo_calendar | import | 1h ago |
Policies
Browse and manage Cedar access policies for your tenant.
| Policy ID | Effect | Resources |
|---|---|---|
merch-read-default | permit | Model::* |
lp-read-shrinkage | permit | Model::"inventory_shrinkage" |
vendor-blocked | forbid | Model::"labor_*" |
fresh-team-west | permit | Model::"fresh_waste_daily" |
Why Shrinkage matters for Grocery retail
Grocery shrinkage splits into theft, spoilage, and admin error, but most retailers can't distinguish the cause until physical inventory. Ward separates these at the store-department level by cross-referencing receiving logs, POS velocity, waste scans, and inventory snapshots to produce cause-attributed shrinkage cards.
What Ward has eyes on.
Ward reads any BigQuery dataset, gA4 event exports, ads data transfers from Google BigQuery on a read-only connection. Nothing is written back, and your Data Platform configuration does not change. BigQuery stays the system of record.
Find the leak before it drains you. Ward runs the model continuously rather than on a reporting cycle, which is why a finding lands the morning the pattern starts instead of at the end of the period.
Every one of your stores gets its own baseline. Ward scans continuously fill rate, shrinkage %, fresh waste % against it and brings up only the deviations that hold up. The two that show up most in grocery retail are fresh waste & spoilage and on-shelf availability gaps, and both are baseline problems before they are P&L problems.
At the metric level. Ward decomposes shrinkage into theft, spoilage, vendor fraud, and admin error, then tracks inventory-to-sales ratios, receiving accuracy, and waste scan compliance by department. Rising shrinkage in a single department usually signals a process failure, not organized crime.
Why this combination
is its own problem.
A generic shrinkage model applied to a grocery estate produces alerts nobody trusts. The thresholds are wrong, because grocery baselines are wrong for it. Ward learns the baseline from your own stores instead of importing one.
- 01 Self-checkout shrinkage is misattributed to staffed-lane theft because the cause-attribution model lumps all front-end voids together.
- 02 Estate-average shrinkage hides the four to seven stores driving 40% of the loss; chain reports never name them.
Benchmarks. US grocery shrink averages 2.0-3.0% of sales, with fresh departments running 4-7% and center store closer to 1-2%. A multi-vertical operator is usually surprised to learn shrink concentrates in three departments per store, not chain-wide, which means three targeted fixes recover more than blanket LP spend.
What the first 90 days
actually look like.
-
01
Week 1: connect
Read-only credentials to Google BigQuery. Ward reads any BigQuery dataset, gA4 event exports, ads data transfers and starts building baselines. First daily cards land inside 48 hours, before baselines are stable, so you can see the shape of the output early.
-
02
Weeks 2 to 3: calibration
Baselines stabilize per store and per category. Ward stops flagging normal variance and starts flagging exceptions. This is the window where the false positive rate drops sharply.
-
03
Weeks 4 to 12: steady state
Ward sends findings every morning, each with the driver and what to do about it. Volume settles at a level a single person can read over coffee. The measure of success is not how many findings arrive, it is how many get acted on.
How Ward connects to Google BigQuery
Ward queries BigQuery using your existing datasets. GA4 exports, POS data, CRM exports. Ward reads it where it lives.
Setup: Service account with BigQuery Data Viewer role. Ward runs read-only SQL queries on your schedule.
Data Ward reads from BigQuery
Impact metrics with BigQuery
Data lake enrichment
Ward enriches BigQuery data with: Any BigQuery dataset, GA4 event exports, Weather & events, Demographics, Custom feeds
You find out about stockouts after customers do.
- ×Demand forecasts are off by 15-25% and nobody catches it until the shelf is empty
- ×Supplier fill rate problems announce themselves at the receiving dock
- ×Safety stock levels get set once a year and left alone
- ×No early warning system for supply chain disruptions
- ×Replenishment exceptions require manual triage every morning
- ✓Stockout prediction cards arrive 24-72 hours before empty shelves
- ✓Supplier fill rate tracking with automatic escalation
- ✓Dynamic safety stock recommendations based on current demand signals
- ✓Weather, event, and macro-driven demand adjustments
- ✓Replenishment exceptions auto-prioritized by revenue impact
Stockouts cost retailers $1.14 trillion in missed sales globally each year. Source: IHL Group
Grocery KPI impact
Frequently asked questions
Ward identifies abnormal inventory loss patterns and distinguishes between theft, damage, spoilage, and administrative error. For Grocery retail specifically, Ward monitors 30,000+ SKUs across your stores and delivers automated insight cards with root cause analysis and recommended actions.
Ward tracks Fill rate, Shrinkage %, Fresh waste %, Promo lift, Basket size at the store-category level. Ward compares expected inventory against actual counts, segments loss by cause category, and flags store-level anomalies against your estate baseline.
Service account with BigQuery Data Viewer role. Ward runs read-only SQL queries on your schedule. Data points include: Any BigQuery dataset, GA4 event exports, Ads data transfers, Custom ETL outputs.
Yes. Ward reads BigQuery data and combines it with contextual signals (weather, events, demographics) to generate Grocery-specific insight cards. No custom development required.
You find out about stockouts after customers do. Ward solves this with automated insight cards: Stockout prediction cards arrive 24-72 hours before empty shelves. Supplier fill rate tracking with automatic escalation. Dynamic safety stock recommendations based on current demand signals.
Ward delivers daily insight cards covering Fill rate, Shrinkage %, Fresh waste %, tailored for Supply Chain decision-making. Each card includes what changed, why it matters, and what to do next.
Ward decomposes shrinkage into theft, spoilage, vendor fraud, and admin error, then tracks inventory-to-sales ratios, receiving accuracy, and waste scan compliance by department. Rising shrinkage in a single department usually signals a process failure, not organized crime.
One store flags elevated shrinkage well above the estate average for two consecutive periods. Traditional LP assumes shoplifting. Ward traces the majority of variance to receiving dock discrepancies in frozen foods, vendor deliveries consistently short against POs. One process fix, mandatory blind receiving, brings the store back in line within six weeks.
First insight cards arrive within 48 hours of data connection. Ward needs approximately 2 weeks to establish stable baselines for your specific operation.
No. Ward sits on top of your existing stack. It is the proactive intelligence layer that watches your data continuously and delivers insight cards, so your team acts on findings instead of hunting for them.
Related solutions
See what Grocery shrinkage problems Ward catches.
Root causes, not just alerts. See it on your data.
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.