A home Head of IT running shrinkage on BigQuery
A home Head of IT on BigQuery should not be hunting for shrinkage problems. Ward brings up them each day.
How a home Head of IT runs shrinkage on Google BigQuery
The business wants AI. You sign off on the architecture. Ward writes the finding at the altitude a Head of IT works at.
What shrinkage detection does: Ward identifies abnormal inventory loss patterns and distinguishes between theft, damage, spoilage, and administrative error.
In a Home Improvement store base the job is 50,000+ SKUs across stores. Project-based purchasing, long-tail SKUs, and seasonal volatility. Ward manages the complexity of 50,000+ SKU environments with ease.
How it runs. 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.
What you get
- Cause-level shrinkage attribution
- Store-vs-estate benchmarking
- Receiving dock anomaly detection
- Pattern recognition across time
Chat
Ask anything. Ward routes to the right agent and returns cited answers.
I pulled the spring pre-build against the last three seasons and the weather signal for the 22 Southeast stores.
| Signal | Finding |
|---|---|
seasonal_prebuild | Mulch on-hand hit 61% of plan the week temps broke 70°F |
dc_push | DC push started 9 days after the first-warm-week trigger, LY it was 2 |
attach.project | Soil and edging attach fell 18% at stores that gapped on mulch |
Recommend: tie the push trigger to the 10-day forecast instead of the calendar week, pre-position two truckloads at the 8 stores that gapped, and re-set the attach endcap.
seasonal_prebuild…
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 |
|---|---|---|
epicor_pos_transactions | import | 2m ago |
epicor_special_orders | import | 2m ago |
netsuite_inventory_snapshot | import | 14m ago |
retail_seasonal_prebuild | import | 1h ago |
retail_sku_velocity | import | 1h ago |
retail_pro_account_sales | import | 1h ago |
retail_weather_daily | import | 1h ago |
Policies
Browse and manage Cedar access policies for your tenant.
| Policy ID | Effect | Resources |
|---|---|---|
merch-read-default | permit | Model::* |
pro-team-read-accounts | permit | Model::"pro_account_sales" |
vendor-blocked | forbid | Model::"labor_*" |
supply-read-orders | permit | Model::"special_orders" |
Why Shrinkage matters for Home retail
Small hardware has the highest per-unit theft rates but lowest dollar impact; power tools have lower frequency but massive loss per incident. Ward segments shrinkage by value tier and department so loss prevention allocates resources where the dollar impact is highest, not just where the unit count is.
What Ward has eyes on.
Every one of your stores gets its own baseline. Ward tracks project basket value, seasonal accuracy, long-tail turn against it and pulls forward only the deviations that hold up. The two that show up most in home retail are project basket identification and seasonal pre-positioning, and both are baseline problems before they are P&L problems.
Ward pulls from BigQuery rather than replacing it. Any BigQuery dataset, gA4 event exports, ads data transfers come across on a read-only connection, get enriched with contextual data, and come back as daily cards. Your Data Platform is untouched.
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.
At the metric level. Ward segments by value tier, tracks geographic clustering for ORC detection, monitors receiving accuracy on bulk/pallet deliveries, and measures POS velocity-to-inventory count gaps.
Why this combination
is its own problem.
A Head of IT does not need the shrinkage model explained. They need to know which stores moved, why, and what to do by end of day. Ward writes the finding at that altitude.
- 01 ORC patterns concentrate geographically; chain-wide LP allocation misses the cluster signal that directs investigative focus.
- 02 High-volume small hardware shrink dominates incident counts and pulls LP attention toward unit-level fixes; the bigger dollar exposure is in low-frequency power tool theft.
Benchmarks. Home improvement shrink runs 1.4-2.6% of sales, with power tools, copper, and high-value building materials accounting for 30-50% of total dollar shrink despite small unit volume. ORC events typically affect a tight geographic cluster of 5-15 stores.
What the first 90 days
actually look like.
-
01
Week 1: read-only connection
Ward connects to Google BigQuery with read-only credentials and begins ingesting any BigQuery dataset and gA4 event exports. No config changes on your side. First daily cards arrive in two days.
-
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 returns cards daily, each with what caused it and a recommended move. Volume settles at a level a single person can read over coffee. The measure of success is not how many insight cards 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
The business wants AI. You sign off on the architecture.
- ×Business sponsor already chose the vendor. You inherit the security review
- ×Every AI vendor wants write access and a copy of the production data
- ×Model lock-in means rewriting the stack when GPT or Claude moves again
- ×Audit trail is an afterthought. Compliance has nothing to pull on
- ×Data lake project keeps getting bumped for the next thing the business wants
- ✓Federated query: data stays in your warehouse. No copies, no shadow lake
- ✓Read-only credentials. Cedar policies enforce least-privilege per agent
- ✓LLM-agnostic. Anthropic, OpenAI, Gemini, Ollama. Bring your own keys
- ✓Every query, every model, every source logged. SIEM-ready audit output
- ✓VPC peering, PrivateLink, SOC 2 II. Your security review is short
74% of enterprise AI projects stall before production. Integration debt and security review are the top two reasons. Source: Gartner
Home KPI impact
Frequently asked questions
Ward identifies abnormal inventory loss patterns and distinguishes between theft, damage, spoilage, and administrative error. For Home retail specifically, Ward monitors 50,000+ SKUs across your stores and delivers automated insight cards with root cause analysis and recommended actions.
Ward tracks Project basket value, Seasonal accuracy, Long-tail turn, Pro customer share, Attachment rate 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 Home-specific insight cards. No custom development required.
The business wants AI. You sign off on the architecture. Ward solves this with automated insight cards: Federated query: data stays in your warehouse. No copies, no shadow lake. Read-only credentials. Cedar policies enforce least-privilege per agent. LLM-agnostic. Anthropic, OpenAI, Gemini, Ollama. Bring your own keys.
Ward delivers daily insight cards covering Project basket value, Seasonal accuracy, Long-tail turn, tailored for Technology decision-making. Each card includes what changed, why it matters, and what to do next.
Ward segments by value tier, tracks geographic clustering for ORC detection, monitors receiving accuracy on bulk/pallet deliveries, and measures POS velocity-to-inventory count gaps.
Ward flags elevated power tool shrinkage at a geographic cluster of stores, concentrated during weekday afternoons, a pattern consistent with organized retail crime. Ward recommends immediate spider-wrap enforcement and receipt-checking at affected locations. LP investigation confirms a theft ring, and targeted intervention brings shrinkage back toward estate averages within 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 Home 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.