# Frequently Asked Questions (FAQ)

#### Which price is predicted by the AVM API?

Altum AI predicts the transaction value or free sale value for the given valuation date.

#### How is confidence measured and how should it be&#xD; interpreted?

The AVM learns to predict house valuations from the actual market values. Once the prediction is generated, the process of estimating the prediction interval starts. The prediction interval divulges where a value will fall in the future and is a great way to estimate uncertainty. This procedure is constructed by a statistical approach which defines a price range for where the 90% confidence interval lies.

#### Is it possible to input dates other than today?

The AVM API as default uses the date of today of entry. It is possible to input a valuation date in the past and then the AVM API will return the value of that given date. It is not possible to give valuations for future dates, if a future date is given as input it will return the valuation for 'today'.

#### How should I input housenumber additions?

House number additions are combined with house letters as follows: B4

#### What is the accuracy of the model?

The model has a Median Absolute Performance Error rate of 3.57%. Go to the [accuracy page](https://altum.ai/accuratesse-altum-ai) on the Altum AI website for a more in depth explanation (Dutch).

#### Why don't I get the latest WOZ-value?

If the valuation date which is given as an input is for example 10-10-2019 we give the WOZ value applicable and distributed for that year which is the WOZ-value from 1-1-2018.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.altum.ai/english/property-valuation-and-market/avm-api/frequently-asked-questions-faq.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.
