Uncategorized

The importance of various factors in calculating the value of housing

Cracking open the black box of machine learning and gaining insights from geodata.
Black-box 

Machine learning models are sometimes referred to as “black-box” models as we don’t know how and what they do. Although building a model with high accuracy is considered the main business goal for most of the companies that adopt machining learning techniques, it is not enough for the owners to know how a model is working. For instance, we know that distance to centre and distance to school might affect the housing value. However, we don’t know if the relationship between them is monotonic, linear or even more complex. To be able to understand their deliverables we reach out to other tools, which help us presenting their outcome.  

 
Visualizations

The partial dependence plot allows us to visualize the functional relationship between the features (distance to the city centre by bike) and the target (housing value) in a non-transparent model such as a random forest model. More specifically, the partial dependent function tells us that the average marginal effect on the prediction for a given value of the feature.

By integrating geodata provided by StraTopo, the machine learning-based housing valuation model explains how location attributes affect house value. 

The picture shows the housing value, before reaching 7k (kilometres) of distance to the center, falls as we get further suburbs in the Limburg area. But the value rises after the distance exceeds 7k, and stabilizes after 11k.

In conclusion, we can see that the price drops dramatically with the further distance to the city centre. which is a common situation. This graph has been prepared for model visualization and StraTopo is currently working on analyzing other factors and presenting their influence.

Want to know more or integrate StraTopo’s data? Contact StraTopo via info@stratopo.nl.

By |2021-09-06T10:32:00+02:00September 6th, 2021|Uncategorized|0 Comments

Childcare accessibility

Convenient access to childcare is crucial for many parents. StraTopo looked into this accessibility for Utrecht – a city recognized as one of the top 10 best Dutch cities to live in with children.

We found that 91% of buildings that have living units in Utrecht have a kindergarten within 15 minutes of walking.

Would you like to know how accessible childcare is in your area?

Reach out to us on info@stratopo.nl !

By |2021-01-06T11:23:55+01:00January 6th, 2021|Uncategorized|0 Comments

Data for Urban Logistics Deephack

Routing engine insights awarded first-prize in Hackathon!

StraTopo successfully participated in Ultrahack’s ‘Data for Urban Logistics’ Hackathon, organized by EIT Digital and Urban Radar. In this competition teams had to focus on creating new conceptual business models for how logistics and delivery companies can make more informed decisions. By doing so, businesses can improve their operations while reducing their impacts on congestion and gas emissions in cities.

Data Driven Decisions

We create algorithms that provide insights which are essential to make decisions towards a zero emission city logistic. Using the Routing Engine, our algorithm calculated the percentage of citizens of a city that can walk within 15 minutes to a package delivery point. This is a starting point for a framework of algorithms to expand on.

Example:

– Providing a heatmap showing the optimal location for introducing bike package delivery or locker placement.

– Calculating the effect on emission and liveability by introducing bike delivery, locker placement or replacing trucks with more environmental friendly vehicles.

Get in touch with s.reulen@stratopo.nl to find out how we can help you.

By |2020-12-09T10:19:24+01:00November 11th, 2020|Uncategorized|0 Comments