Sign in
Set up for Construction and building materials

AI for insights and analytics

AI analytics for construction and building materials

A builders' merchant sells to trades that each buy a known basket. AI analytics compares every account with the trades like it, finds the categories a builder buys elsewhere, watches credit headroom and quote conversion, and answers in figures that tie to the ledger.

Ask it in your own words

These are the questions builders' merchants 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 trade accounts buy a category from someone else?Category share by tradeEach account's category mix against the norm for its trade, with the gap valued at the account's own spend.
Which trade accounts have gone quiet?Dormant trade accounts, by prior valueAccounts past their own order gap, by prior-year value, branch and rep.
Who is about to hit their credit limit?Credit limit headroomHeadroom by account against its run rate, with the ones that will stop being able to buy this month.
How much quote value are we losing, and to whom?Quote conversion, count and valueConversion by count and value per customer and branch, with the lost value listed.
Are we invoicing at the agreed terms?Price realisation against termsInvoiced against agreed prices by line, with leakage by branch and account.
Which projects in the pipeline match accounts we hold?Project pipeline matched to accountsPlanning and project leads matched to existing accounts, with the estimated spend and the current share.

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.

Where are our trade accounts buying elsewhere?

The category gap against trade norms is worth £2.7m a year across 3 trades, valued at each account's own spend. General builders accounts hold £1.4m, 52% of the gap.

General builders£1.4m52% of the total
Groundworkers£800k30% of the total
Roofers£500k19% of the total
The 3 lines sum to£2.7m0 unexplained

Which general builders have the biggest gaps?

3 accounts hold £221k of the £1.4m gap among General builders, 16% of it. All three buy timber and sheet from us and little or no aggregates, where full-supply builders spend a fifth of their basket.

Redmayne Construction£96kaggregates 0% against 18% norm
Hollis & Sons£74ktimber 12% against 32% norm
Parkside Builders£51kaggregates 3% against 18% norm
These 3 are£221k16% of General builders

How do we turn that into orders?

Each account gets a category conversation, not a discount. The rep takes the basket comparison, the delivery slot and the credit headroom, and the branch tracks whether the category appears on the next invoices.

Branch managersVisit the three accounts with the basket comparisonThis fortnight
Credit controlConfirm headroom on each before the visitThis week
Regional sales managerTrack category share by trade monthlyMonthly
Which trade accounts buy a category from someone else?Which trade accounts have gone quiet?Who is about to hit their credit limit?How much quote value are we losing, and to whom?

The measures behind the answers

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

MeasureFormulaFromWhat it tells you
Category share by tradeAccount spend in category ÷ account total, against the median for full-supply accounts of the same trade, for categories most of that trade buysLedger with category; account master with tradeThe builder buying no aggregates; the plumber buying no fittings
Account activationAccounts opened with a second purchase within 90 days ÷ accounts opened, by branchAccount master; ledgerAccounts opened and never used
Dormant trade accounts, by prior valuePrior-year revenue of accounts past k × own order gap ÷ prior-year revenueLedgerTrade customers who moved to another merchant
Credit limit headroom(Limit − balance) ÷ limit, with payment record; accounts over 85% used and paying to termsCredit file; ledgerGood customers who stopped because they hit the limit
Project pipeline matched to accountsValue of planning applications and project starts matched to trade accounts, by branch catchmentPlanning or project data; account masterWhich customers have work coming, and where
Quote conversion, count and valueQuotes matched to orders ÷ quotes decided; by valueQuote log; order fileProject quotes that went elsewhere
Branch coverage of key accountsRevenue of key accounts touched within cadence ÷ key account revenueCRM or call log; ledgerWhether the top trade accounts hear from the branch
Price realisation against termsInvoiced price ÷ agreed terms priceLedger; terms fileTerms not applied; counter overrides
Delivered and collected mixDelivered revenue ÷ total; average delivered drop valueLedger; delivery fileCost to serve; small drops to site
Contribution per accountGross margin − rebates − cost to serveLedger; delivery and order filesAccounts that earn after what they cost

Each measure is worked through, with the export it comes from and what to drop, in Sales KPIs for builders' merchants and construction suppliers.

What the AI model does, and what our tools do

The AI model chooses the measure

From your question and the measures declared for construction and building materials, 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 branch 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 sums to the account's ledger total; every account has one trade or is counted as untyped
ActivationAccounts opened = activated + not yet activated within window + window still open
Credit headroomBalance ties to the receivables ledger
Quote conversionQuotes = converted + lost + open

What it reads

The exports builders' merchants 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 with trade
  • Credit file
  • Planning or project data
  • Quote log
  • Order file
  • CRM or call log
  • Terms file
  • Delivery file
  • Delivery and order files

Who owns each answer

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

MeasuresOwnerCadence
Dormancy; key account coverage; credit headroom listBranch manager; regional sales manager; credit controlWeekly
Activation; quote conversionBranch managerMonthly
Project pipelineExternal sales; branch managerMonthly
Category share by trade; price realisation; contributionCommercial directorQuarterly

Questions builders' merchants ask about AI analytics

What is a trade norm, and where does it come from?

The median category mix of accounts in the same trade at your own branches, computed from your ledger. A general builder is compared with general builders, an electrician with electricians. That is why an electrician buying no aggregates is no gap at all, while a builder buying none is a large one.

Can it see credit before it stops an account buying?

Yes. With the credit limit and balance file, headroom is compared with each account's run rate, and the accounts that will reach their limit inside the month are listed with the amount. The conversation happens before the counter refuses the order, not after.

Does it work across several branches?

Every measure is computed per branch and in total, and the totals reconcile. An account that buys from two branches is one account with two locations, rolled up for share and concentration and split for coverage and quote conversion.

Which file answers the most questions?

The invoice ledger with a trade code on the account. It gives category share, dormancy, price realisation and concentration on its own. The quote log, the credit file and any project lead data each add a question they alone can answer.

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.