> For the complete documentation index, see [llms.txt](https://docs.altum.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.altum.ai/english/sustainability/nta-8800-energylabel-v2-api/houses.md).
# Houses
The endpoint described in this section apply to **ground-bound residential properties (houses)**. These include:
* `Vrijstaand`
* `2 onder 1 kap`
* `Hoekwoning`
* `Tussenwoning`
The model assumes a **single dwelling with its own roof, walls, and installations**, which allows the API to estimate insulation levels, heating systems, and other measures based on building characteristics and machine learning predictions.
## Validation & Prediction Performance
Altum AI conducts quarterly performance testing of the NTA 8800 Energy Label API for Houses using a representative sample of 10,000 addresses with an NTA 8800 determination method. The performance is assessed using Mean Absolute Error (MAE), Median Absolute Error (MedAE), and the percentage of results falling within defined BENG2 and energy-label error ranges.
#### **BENG2 / Energy Label Information Available**
Uses a **statistical model** combined with the **definitive energy label or BENG2** information. The results therefore measure the consistency of the API with the available energy information.
{% tabs %}
{% tab title="Q3 2026" %}
**MAE:** 23.14
**MedAE:** 14.0
**BENG2**
```
18.60% predictions in 5 BENG2 units error range.
36.97% predictions in 10 BENG2 units error range.
64.63% predictions in 20 BENG2 units error range.
81.14% predictions in 30 BENG2 units error range.
89.27% predictions in 40 BENG2 units error range.
94.79% predictions in 50 BENG2 units error range.
96.73% predictions in 60 BENG2 units error range.
97.47% predictions in 70 BENG2 units error range.
97.93% predictions in 80 BENG2 units error range.
98.45% predictions in 90 BENG2 units error range.
98.70% predictions in 100 BENG2 units error range.
99.21% predictions in 150 BENG2 units error range.
99.51% predictions in 200 BENG2 units error range.
99.78% predictions in 400 BENG2 units error range.
99.81% predictions in 500 BENG2 units error range.
```
**Energy Label**
```
94.75% predictions in 0 energy label difference.
99.39% predictions in 1 energy label difference.
99.81% predictions in 2 energy label difference.
99.94% predictions in 3 energy label difference.
99.95% predictions in 4 energy label difference.
99.97% predictions in 5 energy label difference.
100.00% predictions in 6 energy label difference.
100.00% predictions in 7 energy label difference.
100.00% predictions in 8 energy label difference.
100.00% predictions in 9 energy label difference.
100.00% predictions in 10 energy label difference.
```
{% endtab %}
{% endtabs %}
#### **BENG2 / Energy Label Information Unavailable**
Uses **machine learning to predict the energy label or BENG2 value** when definitive information is unavailable. These results represent the API's actual predictive performance.
{% tabs %}
{% tab title="Q3 2026" %}
**MAE:** 47.45
**MedAE:** 29.0
**BENG2**
```
8.13% predictions in 5 BENG2 units error range.
17.89% predictions in 10 BENG2 units error range.
35.25% predictions in 20 BENG2 units error range.
50.22% predictions in 30 BENG2 units error range.
61.41% predictions in 40 BENG2 units error range.
71.19% predictions in 50 BENG2 units error range.
78.41% predictions in 60 BENG2 units error range.
82.73% predictions in 70 BENG2 units error range.
86.16% predictions in 80 BENG2 units error range.
88.92% predictions in 90 BENG2 units error range.
90.89% predictions in 100 BENG2 units error range.
95.95% predictions in 150 BENG2 units error range.
97.89% predictions in 200 BENG2 units error range.
99.72% predictions in 400 BENG2 units error range.
99.78% predictions in 500 BENG2 units error range.
```
**Energy Label**
```
45.67% predictions in 0 energy label difference.
81.87% predictions in 1 energy label difference.
92.99% predictions in 2 energy label difference.
97.34% predictions in 3 energy label difference.
99.12% predictions in 4 energy label difference.
99.62% predictions in 5 energy label difference.
99.87% predictions in 6 energy label difference.
99.95% predictions in 7 energy label difference.
99.99% predictions in 8 energy label difference.
100.00% predictions in 9 energy label difference.
100.00% predictions in 10 energy label difference.
```
{% endtab %}
{% endtabs %}
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.altum.ai/english/sustainability/nta-8800-energylabel-v2-api/houses.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
