Improve real estate with open data and AI

The real estate market holds big opportunities, but is also linked with big, long-term investments and financial risk. Identify patterns and insights in data to increase investment profit.

Predict sound real estate investments

We help you identify the market potential for housing and commercial real estate by predicting long term need. Our predictive models give you the power to invest and develop in areas and segments with the highest potential. How many commercial real estate square-meters will be needed for which kind of companies in which areas? How many houses will be needed for which population segments both now and in the future?

Tenant prediction for commercial real estate

When we estimate that a company will move, 7 out of 10 end up moving within 3 years! This means that you can take control of your development processes and reach potential tenants before they have decided or even begun the decision-making process. Advance your office development projects faster and increase your ROI.

Property risk rating

Our dream is to build the ultimate risk assessment tool. Currently, our model helps you to assess the financial risk of an office building by predicting who could be about to move, identifying long term needs for similar tenants in the area, and understanding/gauging companies’ financial situations. Use our model to understand and optimize the credit risk in any building, be proactive regarding your assets, and improve dialogue with investors and financial institutions.

Superior market intelligence

The real estate sector plays an important role in fighting climate change, especially when it comes to optimizing energy efficiency. Our models can help overcome the challenges of missing energy data. Access accurate and comparable energy data to assess and invest in energy savings – even for building assets that don’t have accessible energy data.

Towards sustainable real estate ESG data

Predicting yearly energy consumption using open data


How AI can help reduce energy consumption in building.

Challenge
Improving buildings' carbon footprint and energy consumption is a challenging task for many real-estate owners. Energy consumption data for buildings is lacking and often not very accessible – in some Danish municipalities, up to two-thirds of buildings do not have publicly available or comparable energy data. Consequently, efforts to identify and renovate energy-deficient buildings are tedious and suboptimal. 
Solution
Our latest project, done in collaboration with a large Danish real estate developer and make:net/evenIoT, aimed to predict energy consumption and potential energy savings from renovation solely using publicly available and easily accessible data. In addition, we wanted to see how this could improve the value for an IoT platform such as evenIoT by complementing real-time sensor data with open data. By leveraging open data and AI techniques, we developed two proof-of-concept models for predicting the yearly consumption and potential energy reduction for Danish buildings.
Benefit
Our model, which combined multiple accessible open data sources, predicted with 87% accuracy the energy consumption of buildings in Denmark, which illustrates the tremendous potential that recent AI methods have in modelling energy usage. The solution also yielded a means for investigating the data-based drivers behind differences in energy usage. Now investors and real-estate owners can better understand and access data regarding energy usage and carbon footprints for existing portfolios and potential new assets.
2/3
buildings in some municipalities don't have registered energy consumption.
87%
accuracy when predicting energy consumption for building.

Meet customers future demands

"We are very satisfied with the collaboration, which not only has been very pleasant but also gives us crucial insights that we can apply to meet our clients' future needs. The innovative combination of data empowers us with the ability to look ahead which makes it easier to be profitable"
Elo Alsing, Market Manager, Skanska
Challenge
Skanska, a Swedish-based global construction company, wished to radically improve their lead generation, increase their ability to identify opportunities, and subsequently convert them by identifying the right customer at the right time. Skanska was not only concerned with present customer needs, but also what customers would want to buy in the future. What matters when a project is completed within a three-year horizon? How could Skanska be proactive and ready to meet customer demands in three years?
Solution
Our model considers parameters such as growth in employees, years on current address, and financial development to predict which companies will relocate in the next 1-3 years. The model is correct 7 out of 10 times it predicts such a relocation, and performs ten times better when compared to a random guess. The result are presented in a Predictive Analytics Dashboard, making it possible to filter between companies and find relevant leads for the next real estate project. This means a higher hit rate, a more efficient sales process, and better, proactive customer care.
Benefit
Skanska uses Tembi’s solution to proactively screen for future tenants for their projects. In a small case study, 40% of phone calls using our solution resulted in showings. Cultivating a relationship with a tenant three years ahead of time creates opportunities to customise buildings and accommodate future needs. In the long run, this approach reduces churn between tenants. At the same time, the early partnership with tenants decreases the risk for investors and stakeholders since cashflow gets insured earlier in the process.
70%
of all relocations are predicted.
10 times
better than a random lead list.
40%
meetings scheduled.
Find out how Tembi can assist your team and company
Book a demo and we will reach to find a suitable time
  • Explore how and where Tembi can create value for you.
  • Get a detailed demo from our expert based on your needs.
  • Pricing is determined based on solutions and markets.