Sign in
Set up for Foodservice distributors

AI for insights and analytics

AI analytics for foodservice distributors

A kitchen that drops from three deliveries a week to two shows up as a small dip on the monthly report and a sixteen percent loss on the delivery file. AI analytics reads the invoice, delivery and order guide files, and answers the question the district manager actually asks: which kitchens are slipping, and why.

Ask it in your own words

These are the questions foodservice distributors ask. Each one maps to a measure our tools compute from your files. The AI model chooses the measure and explains the result; the arithmetic is done by our code, and every total is checked.

The questionThe measure behind itWhat comes back
Which kitchens have changed their delivery pattern?Drop frequency against own patternAccounts whose drops per week fell against their own history, with the day that went and the revenue lost.
Where has order guide compliance slipped?Order guide complianceLines bought against the agreed guide per kitchen and chain, and the lines that moved off it.
Which shorts and substitutions preceded a lost kitchen?Substitutions and shortsShorted and substituted lines by kitchen and delivery day, joined to the accounts that then dropped a day.
Which drops do not pay for the truck?Contribution per dropRevenue and margin per drop less the delivery cost, by route and account.
How much of a chain's sites do we hold?Share at chain and siteSites served over sites in the chain, and category share within the sites we serve.
How are new kitchens ramping?New account rampWeekly revenue of new accounts against the typical curve, with those below it flagged.

A conversation, with the figures

Every figure below was computed by a tool from the rows and checked before it was shown. The lines sum; the percentages match; each line opens to the rows that make it.

How much weekly revenue have we lost to kitchens changing their pattern?

Weekly revenue at risk from pattern changes is $84k across 3 districts, from accounts that dropped a delivery day or halved their order value in the last four weeks. Metro district carries $41k, 49% of it.

Metro district$41k49% of the total
Coastal district$27k32% of the total
Valley district$16k19% of the total
The 3 lines sum to$84k0 unexplained

Which Metro kitchens?

3 kitchens make up $41k of the $41k in Metro district, 100% of the district's figure. Two of them had shorted lines on the delivery day that then disappeared.

The Copper Bistro$18kWednesday drop gone; five shorts on Wednesdays before
Harbour Grill group$14kthree sites down from daily to four days
Linden Street Cafe$9.0korder value halved; guide compliance 61%
These 3 are$41k100% of Metro district

Who calls, and about what?

The call is about Wednesday and the shorts, not about price. The rep goes with the shorted lines in hand and the substitution offered, and logs what the kitchen says.

Metro repsVisit the three kitchens with the shorted-line listThis week
OperationsCheck Wednesday route capacity and the five shorted SKUsBefore the visits
District managerRun the pattern-change list every MondayWeekly
Which kitchens have changed their delivery pattern?Where has order guide compliance slipped?Which shorts and substitutions preceded a lost kitchen?Which drops do not pay for the truck?

The measures behind the answers

Each measure has one formula, one source and one meaning. They are computed per route and rep and in total, and every one carries an identity that must hold before it is shown.

MeasureFormulaFromWhat it tells you
Category share per kitchenKitchen spend in category ÷ kitchen total, against the median for its format and cuisineLedger with category; account masterProteins bought, produce and dry goods bought elsewhere
Drop frequency against own patternDelivery days per week, last 4 weeks, against the kitchen's prior 26 weeksDelivery fileA delivery day given to a competitor
Average drop valueRevenue ÷ drops, per kitchenLedger; delivery fileDrops too small to pay for the truck
Order guide complianceSpend on order guide items ÷ total spend; order guide items not bought in 8 weeksOrder guide; ledgerWhat the kitchen was set up to buy and stopped buying
Share at chain and siteRevenue per site against the chain's own median site; sites below half of medianLedger; account master with chainThe kitchens inside a contract that buy elsewhere
Delivery window adherenceDrops inside the agreed window ÷ drops; drops during service hoursDelivery file with timestampsDeliveries that arrived during lunch service
Substitutions and shortsLines substituted or shorted ÷ lines ordered, per kitchenOrder and shipment filesThe service failures that precede a dropped day
New account rampWeekly revenue in weeks 1 to 12 against the ramp of accounts that went on to stayLedger; account masterNew kitchens that are not becoming customers
Contribution per dropGross margin per drop − delivery cost per dropLedger; delivery file; route costsKitchens and routes that lose money as served
Lost kitchens, by prior valuePrior-year revenue of kitchens past k × own order gap ÷ prior-year revenueLedgerRevenue that stopped, with the closure or the competitor to find out

Each measure is worked through, with the export it comes from and what to drop, in Sales KPIs for foodservice distributors.

What the AI model does, and what our tools do

The AI model chooses the measure

From your question and the measures declared for foodservice distributors, the model picks the one that answers it, and the period and comparison the question implies.

Our tools do the arithmetic

Deterministic code reads the rows, computes the measure, and checks the identities below. The same question on the same data gives the same answer, every time.

The AI model explains, and cites

The AI model writes the sentence around the result, naming the route or account behind it. It states no figure that is not in the result, and every figure links to its rows.

The identities that must hold

Category shareCategory spend per kitchen sums to the kitchen's ledger total
Drop frequencyEvery delivery belongs to one kitchen and one day; drops sum to the route total
SubstitutionsLines ordered = shipped as ordered + substituted + shorted + cancelled
Chain and siteSite revenue sums to the chain total

What it reads

The exports foodservice distributors already produce. Column names are mapped once and the mapping is reused. A file is the way in; scheduled delivery and connections to your systems come with the plan, and every source is listed here.

  • Ledger with category
  • Account master
  • Delivery file
  • Order guide
  • Order and shipment files
  • Route costs

Who owns each answer

An answer is a list with an owner and a cadence, or it is a chart nobody works.

MeasuresOwnerCadence
Drop frequency; lost kitchens; substitutionsDistrict sales manager with operationsWeekly
Order guide compliance; new account rampRep; district sales managerWeekly to monthly
Delivery window adherence; contribution per dropOperations; commercial directorMonthly
Category share; chain and site shareCommercial director; national accountsQuarterly

Questions foodservice distributors ask about AI analytics

How does it know a kitchen's normal pattern?

From the delivery file. Each account's drops per week and value per drop over the prior months are its own baseline, so a bistro that always took three a week is flagged at two, and a kitchen that always took one a fortnight is not. A fixed rule cannot do that; a per-account baseline can.

Can it link shorts to lost business?

Yes, when both files are loaded. The tool joins the shorted and substituted lines to the kitchens that later changed pattern, by delivery day, and lists the ones where a short came first. Whether the short caused the change is the rep's call to make, but the timing is on the page.

What does a district manager need to load?

The invoice ledger, the delivery file and, if you have one, the order guide by kitchen. Route cost per drop turns revenue per drop into contribution per drop. All of it is a file your systems already export weekly.

Is a chain treated as one customer or many?

Both. Sites are rolled up to the chain for share and concentration, and reported separately for pattern changes and compliance, because the decision to cut a delivery day is made in a kitchen and the contract is signed at head office.

See it on your data

Bring a few thousand rows. The data map opens next, every column mapped once, and the first question is answered in minutes. Free, in your browser, no account.