Man vs Machine: Big Data in Real Estate

Editor’s note: This article originally appeared in the April 2022 edition of DS News.

Big Data has been a a hot topic in marketing and business circles for 10 years, and real estate is no exception. The industry is seeing a growing push to leverage market and sales data to automate the buying and selling of homes.

Notable industry leaders have dipped their toes in the water and developed automated valuation models (MY V) intended to inform pricing decisions. However, in the face of a global pandemic and a historic housing shortage, even the most robust models are struggling, with Zillow going so far as to close its doors. iBuying service at the end of last year.

At its core, real estate is about people, not an algorithm. Just like people, homes are all individual, with unique value propositions. It takes human insight to understand each and assess the true value of a home. While market data is extremely important in supporting the price decision, it is not the “be everything and the end of everything.”

The role of data and technology should complement efficiency, not supplant or replace people. There are many dangers in focusing only on Big Data.

Big Data requires a lot of money

“Big Data can help provide information on thousands of comparable properties, instead of just a few, and can be leveraged to analyze market conditions and consumer profiles, among many other datasets, to more accurately establish property values,” explains Jayesh MaganlalChief Information Officer, DAMAC Properties.

However, real Big Data requires extraordinary volumes of information of a wide variety of data sources, which is very costly both from a technology and talent perspective. Real estate simply doesn’t have the full arsenal of data available in other industries. Ours are limited in scope and transactional in nature.

Artificial intelligence (AI) and machine learning (ML) routines require extraordinary input. If you don’t feed the routines massive information, the algorithms will skew the data they have, which can be quite dangerous. Without enough data to be statistically significant, models can provide false automated assessments which do not represent true market values ​​in a fast and dynamic environment such as the one we are currently experiencing.

Big data and bias

“Research has long show these computer models are loaded withprejudices and faults,” noted GeekWireco-founder John Cook. Following Zillow’s decision, the consensus among experts is that iBuying companies trust machines too much to do what humans can do best.

Models typically aggregate and average MLS listing data at the MSA or ZIP code level. But with a limited supply on the market, there are few compositions to consider. And, as we all know, location, location, location is what matters in real estate.

Pricing today occurs at the micro-market, neighborhood and block level, if not at the individual home level, with a range of aesthetic, social and other factors playing a part, like natural light, intuitive layout, level of finish, etc

“The system can capture that there are three bedrooms, but does it capture that they are laid out in a way that makes sense?” comments NYU’s Dean of Real Estate, Sam Chandan.

Examining suggested prices based on town or city averages is highly inaccurate. You need qualified professionals with local experience to assess prices and provide personalized offers. skill ohn Localized shopping habits and preferences.

A rear view

Another important consideration in big data models is data synchronization. By the time it reaches the big data engine, the data is retrospective, 30 to 60 or 90 days old. That may be fine for a stabilized market, but not for a rapidly changing market like today’s.

“All the artificial intelligence and machine learning in the world is not yet up to the complexity of valuing a home in a rapidly changing market,” notes the CEO of MoxiWorks. York Baur.

The pandemic has forever changed the role of the home where we work, eat, play, teach and learn. Space has become critical and layout needs are radically different. “This change in buyer preferences is extremely difficult for a machine learning model to incorporate,” notes BiggerPockets’ vice president of data and analytics. David Meyer.

Cue Zillow’s decision to drop the back home business, an edifying tale on the limits of Big Data. Its algorithms were simply not able to take into account the fluctuations in consumer needs and prices that we have experienced over the past two years and accurately predict future home prices and sales velocity..

Consumers are tired of paying 6% to an agent who may or may not add real value to the transaction and spending too much time and money on a traditional ad. While iBuyers want to offer consumers a simpler solution, the danger lies in relying on a computer to decide the value of a home. iBuyers may have seen significant growth, but the question remains whether that can continue in a volatile and rapidly changing market.

The good thing

So what role should data play in a real estate decision? AT new westernwWe believe data should help accelerate market benchmarkingands (CMA) but that local agents should act as a foothold in the street to provide hyper-local information and information to buyers and sellers.

Many experts agree with us“What this tells me is that we need to stop over-applying technology in an effort to replace humans, and instead focus on applying technology to make humans better,” notes Bauer.

We see a place for Big Data andd AI/ML in evaluating opportunities for our agents. These technologies can be combined so as to find matches between the seller’s opportunities and the buyer’s preferences that result in the most likely candidate coming to the top of the list. Big Data has an important role to play in scoring leads, opportunities, and deals.

Face the future

A recent KPMG study shows a growing interest in digital transformation in real estate, from profitability to improved decision-making. Beyond prices, the data can be used to track demographic and employment trends and help developers identify and develop attractive properties. Add to that apps that use data to project a property’s potential earnings and revenue.

“A developer can thus quickly access hyperlocal community data, combined with land use data and market forecasts, and select the most relevant neighborhoods and building types for development,” reports McKinsey & Company. At New Western, wand also leverage data science analytics to examine predictive indicators and assess opportunities for market expansion. But we’re still relying on people to dig deeper and make the final decision on where we’ll expand next.

Big Data can also play a role in marketing properties. Agents can use search engines and advertising data to refine and target relevant audiences. The sales process is another area where data can be used to create models that measure visitor interactions on competing websites in addition to tracking interaction with advertising.

Data can also be analyzed to assess buyer preferences and strength by reviewing credit scores, mortgage pre-approvals, and other public documents.

While real estate is certainly ripe for disruptions and applications like this, there are many variables that need to be considered for pricing models to become more efficient. The challenge will be how to identify predictive indicators to price the markets – and current market volatility is going to make that difficult at the moment.

Technology and automation have a huge role to play, but it’s not the main one. People will always come first. Information is one piece of the real estate puzzle. But humans will always need to evaluate data with personal instinct, intuition, and experience for make educated business decisions.

Data is a means to an end…it is not the end.

Previous Electronic Systems Design Industry Reports 14.4% Year-over-Year Revenue Growth in Q4 2021, ESD Alliance Reports
Next System Helps Severely Disabled Type Faster and More Accurately | MIT News