Dr. Horton uses prophetic AI to build more homes

A version of this article first appeared in the CNBC Property Play newsletter with Diana Olek. Property Play covers new and evolving opportunities for the real estate investor, from individuals to venture capitalists, private equity funds, family offices, institutional investors and large public companies. subscription To receive future issues, directly to your inbox.

Dr. Hortonthe nation’s largest homebuilder, is tapping an AI tool from Portland, Oregon, startup Prophetic to build more homes and address the nation’s housing shortage.

Chronic construction shortages since the Great Recession have left nearly 4 million homes short, according to analyzes from several sources, including Zillow. The imbalance between supply and demand caused prices to rise by more than 50% from pre-pandemic levels.

Homebuilders are trying to respond, but they say the cost of construction, combined with the difficult and expensive process of acquiring and developing buildable lots, makes it difficult.

“One of the biggest challenges in providing affordable housing is identifying, acquiring and entitlement to suitable land for development. We are confident that the insights provided by Prophetic will help us expand homeownership opportunities for America’s hard-working individuals and families,” Jason Jones, vice president of data analytics at DR Horton, said in a press release.

Prophetic has developed an AI-based platform for land tenure analysis and development. For any potential parcel of land, Prophetic will pull every zoning guide from every city and county in the state. It is currently operating in 25 states, and is expected to be in all 50 states by June.

“It’s a very large, tedious, detail-oriented process, taking tens of thousands of these zoning documents and extracting the rules, not just efficiently, but correctly,” said Oliver Alexander, founder and CEO of Prophetic.

Among other things, the system considers minimum lot size and minimum or maximum density setbacks, which vary by municipality and region. It updates those quarterly.

“Then it tells you where that information came from, which is what mainly sets it apart,” Alexander explained. “When you have that section title and the page it came from, it builds trust, and then it becomes very effective, as you can analyze development potential in 30 seconds instead of two to three hours.”

Alexander said there are just over 440,000 different ways to describe what you’re allowed to do on a piece of dirt in the states analyzed by Prophet. Developers need to look at all this information to know if they can build a single or multifamily residential project on it.

Large-scale analysis of these documents based on the AI ​​language model can answer questions and then feed them into the AI ​​for research, which Alexander calls a “key unlock” – searching plus AI information for the area together. At the ground level, using this AI, builders can see what they can build, where and how much at a much faster pace, making them more competitive with landowners.

“If you have that much of an advantage in speed of decision making, you effectively control the entire market, because before anyone else can make a decision, you have tied them up,” Alexander said.