KB Analytics
Proprietary intelligence for Australian housing, farming and energy.

Predictive modelling · Sydney, Australia

Proprietary intelligence for affordable housing, regenerative agriculture and renewable energy.

Homes are funded years before handover. Farms change practice now for a result a decade away. The grid runs on sun and wind. Our algorithms work through Australia's large public records and tell you how long, how much and how likely, as a range. You see the risk early, and put your money where the chance of success is highest.

Request a brainstormSee the three sectors

KB Analytics Pty Ltd · ABN 18 680 683 827 · Hurstville NSW 2220

Where we work

Homes. Farms. The grid.

Plate Nº I
A housing block part-built, with the statewide average and a forecast range for its finishArchitectural sketch of a three-storey apartment on a slope: the left half finished in brick, the right half timber frame inside scaffolding, a tower crane lifting a wall panel. Construction lines remain on the sheet. A yellow bar marks work built so far and widens into a forecast range; a hairline marks the statewide average.BUILT TO DATESTATEWIDE AVERAGEFORECAST RANGEKB ANALYTICSSECTOR OUTLOOK · AUSTRALIAA BLOCK PART-BUILT — THE FINISH AS A RANGEAFFORDABLE HOUSING CONSTRUCTIONPLATE Nº INOVEMBER 2026 · NOT TO SCALE

Affordable housing

When will this project finish? A date with a range, on the day the money is committed.

See the six questionsPlate Nº II
A paddock in cross-section with soil cores marked for samplingArchitectural section of an Australian paddock: pasture, a gum tree, a fence and a windmill above; roots, topsoil, subsoil and stone below. Construction lines remain on the sheet. A hairline marks the regional mean. Three yellow cores are the samples for this paddock.REGIONAL MEANSAMPLES FOR THIS PADDOCKKB ANALYTICSSECTOR OUTLOOK · AUSTRALIAA PADDOCK IN SECTION — THE SAMPLE POINTSREGENERATIVE AGRICULTUREPLATE Nº IINOVEMBER 2026 · NOT TO SCALE

Regenerative agriculture

What will this paddock do? A range for carbon, feed, water and nitrogen, this season.

See the six questionsPlate Nº III
Wind turbines, a solar farm and a transmission line under a published forecast and a forecast rangeArchitectural and mechanical sketch of three wind turbines on a ridge, solar panels in the foreground and a transmission tower. Construction lines remain on the sheet. A hairline traces the published forecast; a yellow curve traces the forecast: solid where output has been measured, a widening band where it is still to come.MEASURED OUTPUTPUBLISHED FORECASTFORECAST RANGEKB ANALYTICSSECTOR OUTLOOK · AUSTRALIAA DAY OF SUN AND WIND — OUTPUT AS A RANGESUSTAINABLE ENERGYPLATE Nº IIINOVEMBER 2026 · NOT TO SCALE

Sustainable energy

What will the next five minutes bring, and the next ten years? Output, demand and price, as a range.

See the six questions

01What you get

Decide earlier, with fewer surprises.

Big decisions fail on what nobody saw coming. Our own algorithms work through Australia's large public records to show what is likely, and how far it could miss. You decide with that in front of you.

  1. Know soonerSee a late project, a dry season or a price slump while there is still time to act.
  2. Plan for the rangeBudget and schedule for the likely best and worst. Not one hopeful figure.
  3. Back what is likely to workPut money and effort where the chance of success is highest.

02What we built

We start with the published number. We return a range.

Our own method takes the number already in use and returns a range for this project, this paddock, this farm. It is scored on records the model has never seen. If it does not beat the number in use, we say so.

  1. Lock the ruleThe number in use today: a statewide average, a map cell, last year's rate, a no-change forecast.
  2. Build the modelOn Australian records, for the decision that has to be made now.
  3. Give a rangeA range you can check. Not a single figure.
  4. Score itOn records it has never seen, against the rule. Misses are named.
  5. Keep scoringAs each quarter, season or five-minute interval arrives.

What stays private

The models, the features, the scoring, and the way a miss shapes the next range. None of it is published. Client data stays with the client. This site shows the questions and the tests, not the working.

03Common questions

KB Analytics in six answers.

What does KB Analytics do?
KB Analytics is an Australian predictive modelling company based in Hurstville, Sydney. It forecasts outcomes in housing, farming and energy, and gives each forecast as a range, not a single figure.
Who is it for?
People who must commit money or effort before the result is known: housing funders, builders and providers; farmers, carbon project funders and verifiers; and the owners, operators and financiers of wind, solar and batteries.
What do I get?
A range for your decision: how long, how much or how likely, with the cases where the forecast misses. You see the risk early, and can put money where the chance of success is highest.
How is a forecast tested?
Against the number already in use, such as a statewide average, a regional map or a no-change forecast, on records the model has never seen. If it does not beat that number, we say so.
What is proprietary?
The models, the features, the scoring, and the way a miss shapes the next range. None of it is published. Client data stays with the client.
How do I start?
Request a brainstorm. Tell us the sector and the decision. We reply by email and say whether a forecast can help.

04Request a brainstorm

Bring us one decision.

Tell us the sector and what you need to decide. We reply by email and say whether a forecast can help. All four fields are needed. We reply to the email you give.