PODCAST: Just how good is AI at predicting the future?

The way real estate professionals forecast rents – key to calculating how much a building is worth – hasn’t changed much in the past couple of decades.

Artificial intelligence is going to change that.

“The application of AI is going to penetrate the forecasting sphere, changing the technology used and making more data available,” says Alberto Lopez, JLL’s Global Forecast Director.

In this episode of Trends & Insights: The Future of Commercial Real Estate, Lopez, Ryan Severino—chief economist at BGO—and JLL’s Chief Economist David Rea discuss the future of rent forecasting and the role AI will play. It’s part of a series of podcasts episodes on the future of AI and real estate.

The challenge with rent forecasting lies in the data, which isn’t always as robust as economists would like. Historical rent data only spans about four decades.

Severino, who is currently testing AI-driven experimentation in rent forecasting, specifically at the metropolitan area level and the submarket level, says he is tackling the data issue by basically “putting in everything but the kitchen sink.”

“We’re using a fairly limited data set for what we're trying to predict,” he says. “But what we found is that if you use massive amounts of potential explanatory variables, then you can actually do a much better job of predicting rents than you can using traditional econometric methods.”

Severino says they are testing unsupervised machine learning, where they train the model to recognize the patterns from both structured and unstructured datasets, contributing to a self-learning process that generates valuable insights.

“It's just amazing to me what the computer can do, that I simply can't. I just don't have enough time in infinite lifetimes to be able to do the massive amount of computing power that we can do by utilizing the most advanced technology that literally exists in the world today,” Severino says.

As the commercial real estate industry embraces the power of AI and machine learning, there is a growing need to understand the limitations of these technologies.

While AI can offer faster, more efficient, and accurate results, it is crucial for humans to be aware of their biases and consider qualitative variables beyond financial metrics, the experts advise.

"The more we rely on AI technology, the more important it becomes for us to understand its limitations,” JLL’s Rea says. “Ultimately, decision-making will always be in the hands of humans. We need to be aware of our biases and question whether we wholeheartedly believe in the model or if we're blindly trusting it as a black box."

Tune into the episode to hear more about how AI technology continues to redefine the field.