Product

An analyst, not a dashboard

The brief tells you what matters each morning. Every finding comes with its evidence, the calculation behind it and a recommended action — and the analysis pages hold every number behind it.

Morning brief

Three things you should know — before 9am

The first screen is a short brief, not a report: yesterday's numbers, the stores needing attention, inventory at risk, and the three most important findings with a recommended action for each.

  • Picks one finding per area — stores, inventory, pricing — so the brief isn't three versions of the same problem
  • Ranks by dollar impact and statistical strength
  • KPI cards for every standard retail period, with like-for-like comparisons
  • Each finding links to its full analysis and evidence
Dashboard · Nova Specialty Retail (illustrative demo data)
Good morning, Rachel 👋
Here's what needs your attention today.
Revenue
$153.3K4.4%
Gross Margin
42.8%0.8 pts
Stores needing attention
5
Inventory risks
86 SKUs
Revenue at risk
$86.2K
🚨 3 Things You Should Know
Critical
Store 22 has 10 top-selling SKUs out of stock
10 of its top 50 sellers are at zero stock (a typical store has 0). Est. lost revenue $22.1K.
Recommended: Prioritize replenishment; check for a stalled PO.
Critical
SKU-0182 will stock out at 9 stores within 7 days
Demand is up 78% vs its 90-day average. Est. revenue at risk $26.7K.
Recommended: Transfer surplus from Stores 1, 14, 18 and 24, then reorder.
Critical
Store 17 revenue is 42% below expected
$48.2K vs $83.1K expected over 14 days. Largest driver: Watches (−76%).
Recommended: Review Watches range and peak-day staffing.
Inventory

Stop losing sales to empty shelves

The inventory command center shows days of supply, stockout risk and revenue at risk for every SKU in every store, and suggests transfers from stores holding surplus.

  • Filters for critical, < 3 days, < 7 days, overstock and slow-moving
  • Velocity measured before a stockout, so lost sales don't hide demand
  • Transfers keep 21+ days of cover at the source and prefer the same region
  • Product pages show sell-through, discount rate and velocity trend
Inventory command center (illustrative demo data)
SKUStoreOn handDays of supplyRiskRevenue at risk
SKU-0264Store 2200 daysOut of stock$4.5K
SKU-0182Store 341.4 daysCritical$4.3K
SKU-0388Store 2200 daysOut of stock$3.5K
SKU-0182Store 2231.3 daysCritical$3.4K
SKU-0182Store 2662.2 daysCritical$3.1K
Suggested transfer: 25 units of SKU-0264 from Store 19 → Store 22, protecting $4.5K of sales (same region; Store 19 keeps 21+ days of cover).
Insight engine

Eleven detectors that run after every sync

Each detector is a transparent statistical method. None of them is a black box, and thresholds can be tuned per organization.

Store revenue anomaly

Last 14 days vs a weekday-adjusted 8-week baseline, scaled by the chain trend; robust outliers only.

Store availability

Top-selling SKUs out of stock at a store compared with peers, with estimated lost revenue.

Stockout risk

SKUs projected to run out at several stores, using demand velocity that isn't hidden by lost sales.

Gross margin deterioration

Chain margin change split into category rate, mix and discount effects.

Growth with margin decline

Stores growing faster than the chain while their margin falls.

Discount anomaly

Stores discounting far above peers; categories discounting far above their own history.

Category trends

Categories growing or declining against the chain, confirmed by the weekly trajectory.

Store productivity

Sales per employee against peer stores.

Slow-moving inventory

Stock that isn't selling, valued at cost.

Regional performance

Regions diverging from the chain, and the stores driving it.

Marketing efficiency

Channels whose return on ad spend has dropped materially.

Findings about the same store are merged into one — so a revenue gap caused by stockouts is reported once, with the stockout as the cause. Every finding can be acknowledged, resolved or dismissed, and expires automatically once it stops being true.

Explainability

“Why am I seeing this?” on every finding

Open any insight to see the detector, the metric, the comparison, the period, the affected stores and products, each step of the calculation, and the underlying data.

  • Observed facts are shown separately from likely explanations
  • Calculations are shown with formulas and exact values
  • Every recommendation names the evidence it rests on
Why am I seeing this? (illustrative demo data)
Detector
Revenue anomaly
Compared with
Weekday-adjusted 8-week baseline × chain trend
Actual revenue
Σ net_sales, Oct 27 – Nov 9
$48,238
Baseline (weekday-adjusted)
Σ avg(weekday revenue, prior 8 weeks)
$77,451
Chain trend factor
median(actual ÷ baseline) across 30 stores
1.073
Expected revenue
baseline × chain trend
$83,122
Gap
actual − expected
−$34,884 (−42.0%)
Robust z-score
(ratio − median) ÷ (1.4826 × MAD)
−5.08
Observed
Watches −76% (chain −6%); transactions −32%.
Likely
Fewer transactions suggest lower footfall or conversion.
Store analysis

Why each store is up or down

Every store page ranks what drove the change — categories, transactions, inventory availability, discounting — and compares the store with the chain average, its region and its most similar stores.

  • Revenue trend against the comparison period
  • Category performance and top products
  • Stock at risk in that store
  • Revenue per salesperson
Store 17 · store analysis (illustrative demo data)
Store 17 is underperforming by $34.9K over the last 14 days — 42.0% below expected revenue.
  1. 1.Watches−74.2%−$10.2K
  2. 2.Footwear−67.4%−$8.7K
  3. 3.Bags & Luggage−29.5%−$4.3K
  4. 4.Transactions−31.1%521 → 359
  5. 5.Inventory availability−4.0 pts96% of top 50 in stock
Reports & data

Reports your leadership team will read

Daily Retail Brief, Weekly Management Review and Monthly Business Review — KPI summary, biggest wins and problems, inventory risks, store and product performance, and recommendations. Download as PDF.

Shopify POS and Square

Connect once with read-only access; stores, products, stock and in-store sales sync every hour.

CSV from any POS

Upload stores, products, sales and inventory from Lightspeed or any other system. Column names are mapped automatically.

Roles and scopes

Owner, Admin, Analyst, Regional Manager and Store Manager — each sees exactly what they should.

See what your analyst finds in your data.

Book a 30-minute walkthrough, or explore the live demo with a full year of sample data from a 30-store chain.