Woningwaardering Estimator
Estimate Dutch housing valuation points (woningwaardering points) based on six key property characteristics of Dutch self-contained dwellings.
This tool has been made for educational, research and entertainment purposes. It is not intended to be used for commercial or legal purposes. For a more accurate estimation, please use the official Huurcommissie tool.
Enter the following information about the property:
- Year Built: The year the property was constructed.
- Number of Bedrooms: Total number of bedrooms.
- Indoor Area: Total indoor area in square meters, including e.g. storage space, garage etc.
- Outdoor Area: Total outdoor area in square meters.
- Energy Label: Energy efficiency label (G to A++++). See: https://www.ep-online.nl/Energylabel/Search
- Property Value: Most recent valid property value as issued by the government (WOZ waarde). See: https://www.wozwaardeloket.nl/
The model uses a gradient boosting regression algorithm trained on Dutch housing data with a residual standard deviation of 5.22. For more information see: https://huggingface.co/woonstadrotterdam/woningwaardering-ml
The MAE (mean absolute error) of the model is 2.97 points. This means that on average, the model's predictions are off by 2.97 points.
The MAPE (mean absolute percentage error) of the model is 1.91%. This means that on average, the model's predictions are off by 1.91% points of the actual value.
Note: The reasonable rent estimation excludes potential surcharge for having a monumental status or for being newly constructed.
Questions or feedback? Please contact tomer.gabay@woonstadrotterdam.nl