Browse through a collection of quotes from astronauts who view Earth from space, and several common themes stand out. The first is why – as human beings – we haven’t all done a better job of coming together and solving the world’s problems. The second, somehow related to the first, is the fragility of our planet and our very existence.
Then there is China’s first astronaut, Yang Liwei, who remarked, in that endearing way only a Chinese could, that “the scenery was very beautiful but I didn’t see the Great Wall”. Compared to Mr. Liwei’s vision, today’s satellites have become incredibly powerful. The imagery data is used to count cars in store parking lots, to measure the depth of storage tanks that hold crude oil, and to map small plots of land that are in various stages of rice cultivation. There seems to be an ever-growing number of companies finding innovative uses for imagery data, and today we’re going to be looking at one that uses satellite imagery as a single data input to calculate valuations. commercial real estate using artificial intelligence (AI).
Commercial real estate appraisals using AI
Founded in 2014, Dutch startup GeoPhy completed its first disclosed funding round of $33 million just a few days ago to provide insight into property values by combining a variety of different datasets – including satellite images – and then analyzing all the data with artificial intelligence algorithms. People have historically relied on real estate agents to help assign property values using comparable, and the problem with this approach is that all the real estate agent cares about is closing this deal so they can earn a commission. While it’s true that tools like Zillow are changing that, there are a growing number of large datasets that can help provide much more granularity when it comes to accurately assessing a property’s value. .
Where obtaining a property appraisal used to take weeks from initial assignment to final report, GeoPhy eliminates this delay in the flow of information with instant results from their MY V (Aautomated VEvaluation Model) which is dynamically updated with new market transactions on a daily basis. After all, an appraisal is only accurate if someone is willing to pay for it. The result is an average predicted value that is only 5.85% of the actual transaction price, twice the accuracy of traditional valuations for commercial real estate. This level of granularity means their platform is now used by some of the world’s largest lenders and investors with a client list that includes names like Goldman Sachs and UBS.
Big Data for Real Estate Appraisals
The company argues that the challenge is no longer how we can collect the data – it’s all there for the taking – but how we can bring all the data together to add value. For example, if you are thinking of moving into a new office and want to know how accessible it is for your employees, GeoPhy can help. The company provides an “accessibility score” per office that is calculated without human intervention and takes into account variables such as the number of nearby transit stations, traffic intensity and proximity to highways.
The real power is evident in the ability to aggregate this data at the enterprise level. Every day, more than 3,000 variables for the 300 listed real estate companies worldwide are collected, including their 200,000 underlying properties, and real-time valuations are displayed on a dashboard. Think of the value it could have if you’re a private wealth manager in charge of a property portfolio for a neurotic wanker who calls you every time something negative comes out on the BBC about falling property values from London.
It’s hard data that you can come to the table with, innit. A Dutch investment bank, Kempenfound that the number of global real estate companies that can be effectively tracked and monitored in detail has increased fivefold, from 60 to 300. The system can also take into account geopolitical events, such as judging the impact of Brexit on the City:
If you’re at all interested in the methods used to calculate commercial property values, it’s a complicated process due to the unique challenges faced when trying to appraise commercial properties. In the case of residential properties, it is easier to make comparisons because all properties have common attributes (size, number of rooms, proximity to schools, etc.) not to mention that there are many more transactions you can use for comparables. The factors used to determine the value of commercial properties differ widely, and one example they give is crime.
Advanced evaluation methods
It’s all about compromise. For example, a commercial office building in the middle of Oakland, California might be the most accessible when looking at your database of employee addresses. The problem is, it’s such a barren place that the only thing going up is the crime rate. Instead of Oakland, you might choose a nice commercial building in Walnut Creek where there’s less crime but then everyone will complain about the trek. When you start making trade-offs like these with multiple variables, things can get messy quickly. That’s why the company’s machine learning algorithms use a technique called (SHaley Aex additivePnations) or FORM which they detail in a great article on Medium. The diagram below shows the variables that have a significant impact on the valuation model:
Take status for example. On the far left you can see how the value becomes more red. (If you’re colorblind, it just means that for higher status areas, you pay more for less the higher you go. In other words, it’s not linear.) This means that high status areas don’t give you the most bang for your buck. If you think about it, that makes sense. Rich people see the value of money differently from us serfs. In fact, the model has actually hit a brick wall trying to explain how astronomical some of the property prices in London are. In other words, the model understands real estate markets extremely well.
We’ve already talked about 9 startups using AI in real estate, and now we can add another AI use case, commercial property appraisals, to that list. The best part is that over time the ratings will become even more accurate. This is because, unlike real estate agents, machine learning gets smarter over time. Nor will he use manipulative language like calling a run-down building “lovely.” Couple this steady increase in intelligence with new datasets being added to the platform and it’s easy to see why investors have funded this very interesting Dutch AI startup.
Investing in technology is extremely risky. Minimize your risks with The Nanalyze Disruptive Technology Portfolio Report to find out which tech stocks you should avoid. Become a Nanalyse Premium member and find out today!