Blog - StraTopo

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

StraTopo in AI4Cities

Consortium Simtelligence with StraTopo on the lead, together with Amsterdam Data Collective and Logistics Community Brabant has been selected to take part in phase 1 of AI4Cities.

AI4Cities

Simtelligence has been selected to take part in phase 1 of AI4Cities, an EU-funded Pre-Commercial Procurement (PCP) project, aiming to help cities accelerate their transition towards carbon neutrality. The project published its Request for Tenders (RfT) on 01.12.2020, looking for AI solutions that can contribute to the reduction of greenhouse gas emissions in the fields of mobility and energy, two domains responsible for 82% of all greenhouse gas emissions in European cities. Starting in Amsterdam, one of the frontrunners to become climate neutral before 2050 and expanding to other cities the Consortium is delighted to get started.

We were one of the 97 companies and consortia to submit an application following the Request for Tenders. 54 of those were submitted in the mobility challenge, 44 in the energy challenge. Following a thorough evaluation by the AI4Cities Buyers Group, 21 suppliers were selected for the mobility challenge and 20 for the energy challenge. As one of the ‘winning’ suppliers and top 2 of the Netherlands, we will now participate in the project’s Solution Design Phase and will receive 40,000 euros funding to further develop and accelerate our proposed solution in accordance with the input provided by the AI4Cities Buyers Group.

Simtelligence

Our consortium consists of three members: StraTopo – a dynamic Geo-Informatics start-up, which provides spatial data solutions, Amsterdam Data Collective – a boutique end-to-end data-science-advisory with Public Sector experts, and Logistics Community Brabant, which connects organisations in a search for logistics innovations. We are excited to begin the solution design phase where we will validate and compare the added value of the product Simtelligence.

Solution

Multiple cross-country initiatives under the umbrella of Sustainable Development Goals require the mobility sector to make significant changes. Hence, with CO2 reduction in mind, Simtelligence is the proposed solution of the current Consortium that will assist in facilitating traffic related improvements and will provide new insights to assist governmental decision makers in making the right investment decisions, which are in line with set public and private policies. Based on the simulation of human mobility behavior, Simtelligence will allow users to predict and to measure the effect of spatial changes on key metrics, while staying close to reality. This way what is decided in the present will have a positive impact on the future.

The AI4Cities Buyers Group consists of lead procurer Forum Virium Helsinki (representing the city of Helsinki), Cap Digital (representing Paris Region), the city of Amsterdam, the city of Copenhagen, the city of Stavanger and the city of Tallinn. These six cities and regions have developed ambitious strategies and policy plans to become carbon neutral by – at the latest – 2050. In AI4Cities they joined forces to go through a Pre-Commercial Procurement (PCP) project process, aiming to procure non-market ready solutions which can help them accelerate their transition to carbon neutrality by utilising artificial intelligence and related enabling technologies – such as big data applications, 5G, edge computing and IoT. Their choice to focus on energy and mobility-related challenges is informed by the fact that these two domains are responsible for 82% of GHG emissions in Europe’s cities.

We are happy to have gotten the opportunity to further develop this idea in the next three months. Following these three months, the AI4Cities Buyers Group will evaluate which suppliers will continue to Phase 2, the prototyping phase of AI4Cities. You can follow the progress of AI4Cities on the project website.

By geomaster|2021-05-25T12:32:59+02:00May 5th, 2021|Events|0 Comments

Livestment for Urban Mobility Hackathon

48 intensive hours of product development, a very informative learning opportunity and a great time during the international Urban Mobility Hackathon

Through creating product Livestment, StraTopo’s geo enthusiasts competed against 23 teams from more than 30 countries to find creative, useful and sustainable solutions for climate-neutral mobility.

During the hackathon, we presented new insights into Sarkandaugava and Bolderaja (neighbourhoods of Riga), through spatial analysis using open data. These included an analysis of existing facilities and their reachability. These insights can help in the connection of sustainable policymaking with investment opportunities in both of these neighbourhoods.

Problem

Throughout the hackathon, we talked to Riga city planners and confirmed that like other cities, Riga’s city planners have a hard time demonstrating how real estate developers would profit from the city’s sustainable, spatial development vision.

On the other hand, we spoke with real estate developers, who acknowledged that there is no geographic tool that can assist them in making profitable investments. This becomes increasingly important as cities become more decentralized.

Solution

Our proposal is a one of a kind tool that gives quick and valuable insight into:

accessibility of existing neighbourhoods (using routing over existing infrastructure),
their demographic and economic characteristics,
city development plans and much more.

Livestment

The possibilities of this tool are truly limitless! The idea is based on the 15-Minute Neighbourhood concept which encourages that within an urban context work, shops, health care, education and entertainment should ideally all be reachable within 15 minutes by foot or bicycle. It emphasises the importance of ensuring access to all locations where people’s daily needs and visits occur. This idea has a proven record of increasing property values, enhancing the quality of life and facilitating a diverse city development.

Based on the identified user needs, we validated the idea and created the first prototype.

Urban Mobility Hackathon, is a project funded by EIT Urban Mobility and organised by VEFRESH, City of Riga, EDI-Institute of Electronics and Computer Science, Teikums co-working and EIT Urban Mobility. The event’s lead partner is the Embassy of the Netherlands in Latvia, and it is also supported by Accenture Latvia and LMT.

Our team learned a lot and came up with a fantastic new solution during this process. We had a wonderful time together, and it was a great opportunity for team bonding!

Urban Mobility Hackathon, thanks a lot!

By geomaster|2021-04-19T14:07:22+02:00April 19th, 2021|Events|0 Comments

Increase your ROI of billboard advertising

Do you offer billboard advertising but question whether your Return on Investment (ROI) can be increased? Or maybe you are looking for a new attractive location?

Most of the Dutch population can be reached through billboard advertising. It can be a great and cost-effective way to increase brand recognition, however to take advantage of its true potential you need to know how to accurately value this advertising.

The role of technology has become increasingly important in finding new opportunities, improving sales, and calculating the reachability of clients. The same trend is happening in the advertising industry. Uniform prices are used by advertising companies, which set prices according to billboard type and their value calculated.

ROI

How?

StraTopo is using our machine learning technology combined with geodata to measure the advertising value of billboards. A popular method of calculating billboard value is Daily Effective Circulation (DEC). We are improving this method by combining the DEC with geo and reachability data.

We use:

traffic data
demographic data
mobility, data about when and how often people travel during the time
StraTopo’s unique geodata: reachability calculations through our Routing Engine and Location-Based Machine Learning

We measure how many people (based on their age, style of living, occupation, type of job, interests) could reach your billboards. We could also check the type of facilities in the area to find the best fit for your advertisement’s purposes (for example; gyms will collect many people interested in a healthy lifestyle).

Through our cooperation, you can gain a unique insight into the market, and based on the results, your organization can create effective advertising campaigns on billboards.

By geomaster|2021-02-09T09:30:42+01:00February 8th, 2021|Geodata|0 Comments

Unlocking the Power of Machine Learning

Machine Learning is an application of Artificial Intelligence (AI) that has a major impact on the world. It is used by many different industries to turn data into insights, and understand the world in ways which are otherwise hidden. Some people don’t know the processes involved when applying Machine Learning, in this post we want to shed some light on that.

Great news!

You don’t have to be a data scientist to get the benefits of machine learning. At Stratopo, our team of experts handles the technicalities, walks you through the process, and allows you to reap the rewards.

At StraTopo we remove all the mystery from machine learning by engaging our clients in the process. We take you through the development stages step by step to help you understand the value that is added to your projects.

A process that is transparent reassures you of the usefulness of the project and creates clarity around expectations.

We believe that the key to a successful project lies in its usefulness to our clients and we maximize it through user-friendly explanations, demo sessions, unique geodata inputs and continuous communication throughout the geospatial project.

Main Steps in the Process:

Defining the challenge – Together with the client, discussing project specifications
Pilot – Data acquisition and exploration
Action plan with agreement and clear deliverables -Reviewing the initial findings with the client to ensure correct understanding of the dataset
Produce model – Build an algorithm
Reviewing and delivering results for the client – Live experiments and showcase to the client
Optional: Build as API
Optional: Build in self-improving models

Building an API

An API, an “application programming interface”, is a computing interface that enables two pieces of software to work together. Based on the delivered Machine Learning model(s) we can make an API so that you can connect the power of the ML models to other pieces of software, thereby empowering your business even more.

Self-improving models

We can even take it a step further and build self-improving models for you. These kind of ML models continuously improve themselves, enabling you to skyrocket your companies’ ability to discover new business opportunities.

Get in contact with our team via info@stratopo.nl to find out more about how Machine Learning can help your company.

By geomaster|2021-02-08T13:55:58+01:00February 2nd, 2021|Data Science|0 Comments

Survey results: essential facilities within 15 Minute

Our Intern Remo is working at StraTopo on his project ‘Geo-Design Within the 15 Minute City Concept’. One of the first steps was to analyze and establish essential facilities in the city. In order to collect data we published his survey on the topic.

Now, the final results from Remo’s survey are in! In the chart below you can see what people find the most essential facilities in a city. These facilities must be reachable within 15 minutes of walking, to qualify it as a 15 Minute City.

You can see the distribution of votes in the chart besides. Only essential facilities belong to the 15 Minute City concept, and these are the places we wanted to find via this survey.

Grocery Shops, Bus Stops and Pharmacies as the Most Essential

All 146 participants found grocery shops, bus stops and pharmacies to be the most essential facilities. Of the participants of the survey, 60% were defined as women, and 40% as men.

Some other interesting results:

1 of 3 participants aged below 30 years, found bars/pubs an essential facility in a 15 Minute City.
All participants aged above 40 years found health centers/ hospitals the most essential facilities in a 15 Minute City.
Participants aged below 30 value health centers/ hospitals 38% less.
50% of men found sports facilities essential in a 15 Minute City, while only 38% of women feel the same.
53% of the workforce (aged 20-64) find office/ working space an essential facility. This assumes working from home has become more popular and people have realised other working conditions.

If you want to learn more or analyze if your city belongs to the 15 Minute City concept, contact us at info@stratopo.nl.

By geomaster|2021-01-28T14:41:48+01:00January 28th, 2021|15 Minute City|0 Comments

High Quality Multimodal Network

Enabling Mobility Experts to Focus on Mobility Insights with a High-Quality Multimodal Network

High quality and an up-to-date network are important for your spatial analysis.

StraTopo can support you in this task by providing continuously updated networks that you need. Our networks are specifically processed to be connected with high precision with the surrounding spatial environment (facilities, housing, etcetera).

Available networks for multiple modalities

We offer this service for the following modalities: bicycles/pedestrians/cars. You can order a specific network for a modality or an all-inclusive one.

Connected to buildings and environment

Our solution works in any geographic area, from a small area to a region to a country. For the Netherlands, we have connected existing topography (like the BAG, which contains all buildings and addresses in the Netherlands) to a routed network. With this connected data you can use straightforward routing modeling to calculate the number of reachable addresses, people, or buildings.

We can connect any type of data to the networks making your geodata analysis straightforward, fast and highly valuable. On demand we can assist you in executing your spatial analysis.

Automatic updates

StraTopo offers automatic weekly updates. OSM data is not ready to be processed immediately. Additionally, time-consuming steps are necessary as well as quality checks. We have automated this process.

Contact us via: info@stratopo.nl.

By geomaster|2021-01-27T10:44:04+01:00January 27th, 2021|Geodata|0 Comments

Retail Network Optimization for Pharmacies

Our next example of geo data use for retail network optimization is reachability calculations of pharmacies in cities.

Pharmacies play an important role in the quality of healthcare of citizens, and having them easily accessible is vital to people who rely on repeat prescriptions, have mobility issues, or are otherwise too unwell to travel.

New Pharmacy location

When planning a new pharmacy, you should take into account such factors as: Is it available to customers from their addresses within 15 minutes of walking? Where are your competitors located? Is it close to medical facilities? Pharmacies belong to ‘’essential retail’’ in a 15 Minute City.

Pharmacy importance during COVID-19

During the lockdown, people avoid direct contact with others. As an effect, they prefer to stay near their houses and treat themselves with medication available across the counter. This need will grow as EU-governments expand COVID-19 vaccines and tests to pharmacies.

Reachability analysis helps pharmacies choose the optimal locations for clients to pick up their vaccines. Result: clients’ travel times decrease dramatically, which reduces unnecessary movements in Covid times. Vaccines are distributed more easily and pharmacies are less likely to become overcrowded

Are you well connected to pharmacies? Which areas in Maastricht will have the easiest access to pharmacies in general?

Want to find out how StraTopo’s Routing Engine can provide analysis and help find optimal business locations within your city?

Get more insights by contacting StraTopo via the contact form or via email: info@stratopo.nl.

By geomaster|2021-01-19T09:33:37+01:00January 18th, 2021|Routing Engine|0 Comments

4 Benefits of Using Geo Data for Retail Network Optimization

Catchment areas of retail chains

Reachability insights can assist with both the commercial planning for retailers, as well as help city planners improve the liveability of their city. In this example, we looked at grocery stores in Maastricht.

With this data, you can easily interpolate the number of citizens closest to a specific supermarket or link other demographic data such as age or income

Business Location Opportunities

Defining the catchment areas of grocery stores helps chains identify opportunities for new attractive store locations and which locations are ineffective.

Market Research

Reachability insights can improve supermarket’s understanding of the client’s preferences based on their address.

Advertising

It also shows also show which areas should be focused on advertising and marketing campaigns (eg. flyers)

Liveability Level

From a citizen’s perspective, living near a grocery store makes life easier, especially for households on a tight schedule who may not have time to grocery shop more than once a week.

When supermarkets are far away, grocery shopping becomes more time-consuming as people must travel further. As a result, many people turn to less nutritional options such as convenience stores and fast-food. Close reachability to grocery stores has other advantages, such as a wider selection of food and lower prices of products.

The map shows the proximity of buildings to grocery stores in Maastricht. Based on this information, we can infer the clientele catchment area for various chains of grocery stores in Maastricht.Grocery stores usually have low density, and their catchment areas contain several neighborhoods, depending on the size of the city.

Do you want to gain more insights into services (and other facilities) accessibility in your city? Get in touch with StraTopo via our contact form or send an email to info@stratopo.nl

By geomaster|2021-01-17T17:46:44+01:00January 10th, 2021|Routing Engine|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 geomaster|2021-01-06T11:23:55+01:00January 6th, 2021|Uncategorized|0 Comments