Home/Offers/Real Estate & Property/Building Energy Scoring API

Real Estate & Property

Building Energy Scoring API

Your portfolio's energy position is probably a column of certificate ratings, many of them a decade old and some of them visibly wrong.

Mortgage lenders
Asset managers
Housing providers
Retrofit contractors
Property software vendors

Discuss This Build See What It Returns

What your customers would see

example interface

MockupIllustrative mockup of the interface we would build. Figures shown are examples, not results from a live deployment.

The problem this solves

Energy performance has moved from a disclosure item to a financial one. Lenders report on the efficiency of their mortgage books, landlords face minimum standards with dated deadlines, and asset managers are asked to price transition risk across portfolios. The data everyone reaches for is the energy performance certificate, which was never designed to carry this weight.

Certificates are assessed on standardised assumptions rather than measured consumption, they can be ten years old, and they reflect the building as it was on the day of the visit. A property with new windows and a heat pump installed since assessment still carries its old rating. Across a portfolio of thousands, the aggregate picture is a blend of stale records and modelled assumptions, and nobody can say by how much it is wrong.

Improving on it means modelling the building from its physical characteristics — age, construction type, form, exposure — and then reconciling that against whatever records exist, including certificate history, installation records and metered consumption where it is available and lawfully usable. The output should be honest that it is a model, with a range, rather than another single letter pretending to be a measurement.

Who buys this

Mortgage lenders, Asset managers, Housing providers, Retrofit contractors, Property software vendors

Category: Real Estate & Property

What the API returns

What comes back

Modelled efficiency estimate with an uncertainty range, alongside any certificate record
Discrepancy flags where the modelled position and the certificate disagree materially
Retrofit measures ranked by cost, saving and disruption, with indicative costs
Estimated energy consumption and cost under current and improved specifications
Compliance position against applicable minimum standards, with the deadline attached
Portfolio benchmarking against comparable stock by age, type and region
Carbon intensity estimates for reporting purposes
Data-provenance marking per property: certificate, modelled, metered or user-supplied

Endpoints

Method	Path	Returns
GET	/v1/buildings/score	Modelled efficiency for one property
POST	/v1/buildings/score/batch	Portfolio-scale scoring
GET	/v1/buildings/retrofit	Ranked retrofit measures with indicative costs
POST	/v1/portfolio/compliance	Compliance position across a portfolio and deadlines
GET	/v1/benchmarks	Benchmarks by age band, construction type and region
POST	/v1/consumption/ingest	Push metered consumption to calibrate the model

Request and response

illustrative

Request

{
  "address": { "line1": "14 Ashbourne Road", "postcode": "LS8 2QR", "country": "GB" },
  "attributes": {
    "property_type": "semi_detached",
    "year_built": 1935,
    "floor_area_sqm": 94,
    "wall_construction": "cavity_unfilled",
    "glazing": "double_pre_2002",
    "heating": "gas_boiler_non_condensing",
    "loft_insulation_mm": 100
  },
  "include": ["retrofit", "compliance", "benchmark"]
}

Response

{
  "modelled": {
    "rating_band": "D",
    "score": 61,
    "score_range_80": [56, 67],
    "basis": "modelled_from_attributes",
    "confidence": "medium"
  },
  "certificate_record": {
    "band": "E", "score": 52, "assessed": "2014-06-03", "age_years": 12,
    "discrepancy": "modelled_better_than_certificate",
    "likely_cause": "cavity fill or boiler replacement since assessment"
  },
  "estimated_consumption": {
    "space_heating_kwh_pa": 11400,
    "total_kwh_pa": 14800,
    "cost_pa": 1420,
    "carbon_kgco2e_pa": 2780
  },
  "retrofit": [
    { "measure": "cavity_wall_insulation", "indicative_cost": 1100,
      "annual_saving": 230, "band_after": "C", "disruption": "low", "payback_years": 4.8 },
    { "measure": "condensing_boiler", "indicative_cost": 2800,
      "annual_saving": 190, "band_after": "C", "disruption": "medium", "payback_years": 14.7 },
    { "measure": "air_source_heat_pump", "indicative_cost": 9600,
      "annual_saving": 140, "band_after": "B", "disruption": "high", "payback_years": 68.6,
      "note": "payback depends heavily on tariff; fabric measures first" }
  ],
  "compliance": { "standard": "minimum_band_for_letting", "current_position": "compliant",
                  "position_at_next_threshold": "at_risk", "threshold_date": "2030-04-01" },
  "benchmark": { "cohort": "1930s_semi_detached_GB_NW", "percentile": 48 }
}

Where the data comes from

Energy performance certificate registers	Published certificate data, which gives assessed ratings and recorded building attributes — with an age problem that has to be handled explicitly
Property attribute and age data	Construction era, type, form and floor area, which drive the physical model where certificate data is missing or stale
Installation and grant records	Published records of insulation, heating and renewable installations, which identify properties whose certificate is out of date
Metered consumption data	Where lawfully available and consented — the only real calibration for a modelled estimate, and the most constrained input
Retrofit cost data	Installed measure costs from published schemes and contractor pricing, which make the measure recommendations costed rather than generic
Climate and degree-day data	Regional heating demand, so a property in a cold exposed region is not benchmarked against a mild one

On data licensing. Being allowed to read a dataset does not automatically mean you may redistribute it, resell it through an API, or train a model on it. Before any build starts we check the licence, terms and derived-data rules of every source, and we design around the ones that do not permit your intended use. Where a commercial licence is required, that cost is identified during discovery rather than discovered later.

The intelligence layer

The difference between a demo and a service is mostly in this section. These are the parts that keep the answer trustworthy once real traffic is hitting it.

A physical building model from construction era, form, fabric and exposure, rather than a statistical fit to certificate scores which would inherit their errors
Reconciliation of modelled output against certificate records, with disagreement surfaced as a flag rather than averaged away
Calibration against metered consumption where it is available and consented, which materially narrows the uncertainty range
Retrofit sequencing logic that puts fabric measures ahead of heating replacement, because the opposite order produces oversized systems and poor outcomes
Indicative cost estimation per measure with regional adjustment and an explicit statement that a survey will change the figure
Uncertainty quantification that widens where attribute data is sparse or the certificate is very old
Validation against properties with both metered consumption and full attribute data, reporting error by construction era and type
Monitoring on certificate register updates and on model bias as building stock and standards change

What it changes for the business

Portfolio position you can defend

Reporting rests on a modelled estimate with a stated range rather than on a column of stale ratings.

Targeted retrofit spend

Ranked measures with payback direct capital to the properties and measures where it does most.

Earlier compliance warning

Properties at risk against a future threshold are identified years before the deadline.

Lending risk visibility

Transition risk across a mortgage book becomes measurable at property level rather than estimated in aggregate.

How it fits into your product

How it embeds

Single call by address for use inside an origination, survey or asset management workflow
Batch endpoints sized for mortgage books and housing portfolios in the hundreds of thousands
Compliance reporting endpoints aligned to the standards and deadlines in your jurisdiction
Consumption ingestion so your own metered data improves estimates for your own stock
Provenance marking on every property, so a report can distinguish modelled from measured
Deployment inside your environment where borrower or tenant data cannot leave

Included in every build

Authentication, scoped API keys and per-customer rate limiting
Input validation with predictable, documented error responses
Versioned endpoints so your integration never breaks without notice
Request and response logging for audit and dispute resolution
Latency, error-rate and usage monitoring with alerting
OpenAPI specification, sandbox environment and client examples
Backups, failover design and a documented recovery procedure
An agreed support arrangement once the service is live

How we would build it

about 12 weeks

Discovery and data review

Weeks 1–2

We agree the exact question the API answers, review the sources you already hold, check what has to be licensed, and write down the response contract your developers will code against.

Architecture and prototype

Weeks 3–4

You get a written architecture plus a working endpoint on real data — narrow, but genuinely callable — so integration can be tested against something concrete rather than a document.

Production build

Weeks 5–10

Pipelines, models, storage, authentication, rate limiting, logging, tests and documentation. Security and observability are part of this phase, not a later one.

Integration and handover

Weeks 11–12

We support your engineers through their integration, run load tests at your expected volume, and agree how the service is monitored and supported once it is live.

Commercial models

There is no fixed price list, because the cost is driven by data complexity, integration count, model requirements, request volume and the support level you need. Scope is agreed in writing before development starts.

Fixed-scope prototype

A defined slice of the service, built and priced as one piece of work. The usual first step when the business case needs proving internally.

Fixed-price build

An agreed scope against a written architecture, delivered for an agreed price. Best when the requirements are already clear.

Build then retainer

We build the service, then operate and improve it under a monthly agreement covering monitoring, updates and model maintenance.

White-label product

The service runs under your brand, your domain and your pricing, with MLPivot invisible to your customers.

Questions buyers ask

Is this more accurate than an energy certificate?

Often yes for older certificates, because it models the building as it is described today rather than as it was assessed years ago. But it is still a model, not a measurement, and for a recently assessed property with a thorough survey the certificate may well be better. The response returns both, flags disagreement, and marks which basis was used — we would rather expose the conflict than pick a winner silently.

Can it replace a retrofit survey?

No. It identifies which properties merit a survey and what measures are likely to pay, which is genuinely useful at portfolio scale. Indicative costs are planning figures; the actual cost depends on access, condition and what the installer finds, and on an older building that difference can be large.

Can you use smart meter or billing data?

Only with a lawful basis and the appropriate consent, which in most jurisdictions means it is available for your own stock or customers and not generally. It is the single most valuable calibration input, so we pursue it where it is genuinely available, and we build the model to work without it, with wider ranges, where it is not.

Does it work for commercial buildings?

Partly. The physical modelling approach transfers, but commercial stock is far more heterogeneous in use, occupancy and servicing, and the benchmark cohorts are thinner. We would scope commercial separately and be explicit that the uncertainty ranges are wider than for residential.

How do you handle properties with no attribute data at all?

They are modelled from construction era, type and regional stock characteristics, with a wide range and a low-confidence marker. For a portfolio report that is often adequate; for a decision about one property it is not, and the confidence marker exists so your workflow can treat the two differently.

All Real Estate & Property offers →

Want this built for your platform?

Tell us what your product does today and what you want another system to be able to ask it. We will come back with an approach, a scope and a price.

Discuss This Build Browse All Offers