We talk about the data science under the hood of our products, some of the (technical) challenges we face and how we solve them, our views & opinions and our customer successes.
Corona Direct launched a new home insurance product. With Rock.estate's building data they have removed a lot of friction from their underwriting process.
COVID19 has led to a significant decrease in real estate transactions in March and April. Publicly available transaction prices can help the path to normalization.
Zimmo's Prijswijzer has been running in production for a week. The analysis of the user statistics led us to several interesting insights.
Zimmo has launched a new website to help its users estimate the price of a house. Rock.estate has built the predictive model behind the application.
The what, the why and the how with a particular focus on open geo-data.
Home insurers put a lot of focus on a building's reconstruction value to calculate its different risks. This value has flaws, while more objective building characteristics remain un(der)used.
Publicly available transaction prices can make the real estate market more transparent. France is showing the way with their recently launched open data portal.
Although heatmaps come with many pitfalls, we believe it is a good idea to interpolate listed asking prices and turn these interpolations into a heatmap using kriging.
A WMTS (Web Map Tile Service) journey in the Belgian coordinate system.
Aiming for 100% matched addresses or only match addresses where you are 100% sure? Make sure you understand your choice and its consequences.
Why 2D needs 3D: correcting building perspective in orthophotos.
Although automated feature engineering is hot today, we still highly value feature engineering based on background knowledge. We demonstrate this approach with an example.
Challenges encountered while computing volumes and how to cope with them.
Fosdem gets better year after year: we saw lots of familiar faces in the geospatial dev room, we gave a talk and list some other talks we liked.
Can we estimate the potential for solar energy for each roof in Flanders based on our 3D models for buildings? And what about the Zonnekaart of the Energie Agentschap Vlaanderen?
Quickly make an interactive presentation with two lines of CSS
Combining the strengths of pdal, ipyvolume and jupyter.
Using open aerial images, a list of 1,000 addresses with swimming pools, and gdal, aws and scikit-learn as data science tools.
Access real estate data for any address (currently limited to Belgium)
Do you want to know more about how we could help you? Don’t hesitate to get in touch with us.
