Algorithms can outperform human experts in fields where data is rich and deep, allowing for continuous feedback loops and learning models that can adjust and refine over time. Commercial Real Estate used to lack a comprehensive and sufficiently deep database until GeoPhy developed its proprietary data management platform. Using supervised learning and neural nets, our models become more accurate every day.
“This is the first true application of big data in commercial real estate.”
Getting an appraisal used to be a process that took weeks, from initial assignment to final report. This lag in information flow is now obsolete with an instantaneous result from a model that is updated on a daily basis with new market transactions
We measure the accuracy of our models by comparing our valuations to the flow of sales prices in the market as transactions close. Our current model accuracy is an MdAPE (Median Absolute Prediction Error) of 7,9%. This means that our median predicted value is just 7,9% from the actual transaction price, which is twice as accurate as the traditional appraisal process for commercial real estate.
We are so used to the way traditional appraisals are done that their lack of accuracy tends not to register anymore. The GeoPhy models are a game-changer for the world of commercial real estate.