Is it too late to wish a very happy new year? It has been a long minute having taken a break in December last year, and before we can settle into this year it’s already February. May this year bring smarter real estate investments to us all. Speaking of smartness, recently I have been seeing ChatGPT pop up in my online feeds. ChatGPT is one of the latest inventions within the broader Artificial Intelligence (AI) trends.
In the simplest of terms, AI is training machines to imitate or reproduce human tasks or to perform cognitive functions as humans do; such as perceiving, learning, reasoning and solving problems. Real Estate delivery and services have very much not been left out of the disruption. My curiosity got me searching and I came across a great piece, excerpts of which I would like to share. Credit goes to the writer Sanksshep Mahendra for the piece which originally appeared in
www.aiplusinfo.com. Have a read and give feedback as always.
AI Improves the Home Search Experience
It’s very daunting for people to search for a new home or office building that perfectly matches their unique needs. Information technology helps people to search for homes seamlessly, thanks to the searchable listings online that has made the whole process more streamlined. Almost all the home search solutions allow interested buyers as well as real estate agents to narrow down their search. The solutions achieve specific search functions by providing several types of filters such as location, number of bedrooms, area, and others. Undoubtedly, this technique is very useful and saves lots of time. Still, this technique leaves almost all the people with far more options than their requirements, and that doesn’t exactly solve the problem. That’s where AI jumps in to save the day.
Many modern searching solutions utilise the same search criteria in order to figure out the customer’s interests and preferences. These solutions choose properties and characteristics based on customer’s search behaviour to create short and more precise listings. Such listings only contain the best-matched results that customers are looking for, which saves both time and confusion.
For example, Zillow takes the search history of a particular customer and combines it with somewhat similar search patterns to create a list. This list contains the results that most of the prospects with similar searching behaviour actively search. It allows the system to only show the results that a customer is most interested in. It works just like the way Amazon’s book recommendations algorithm does.
Many organisations have come up with applications and solutions powered by AI that serve the customers with a conversational interface. These solutions can answer both easy and complex questions, such as:
How many cars can the garage of a certain house accommodate?
Does a particular house have a pool?
How many rooms have attached baths?
These applications add an extra and very impactful layer of detail that drastically reduces the searching time.
Artificial Intelligence Prevents Budget Overruns
This is yet another very important area wherein AI helps both customers and real estate agents. That’s because construction doesn’t have a very extensive history of experiencing budget overruns. The Sydney Opera House’s construction is one of the most popular examples of a budget overrun – it was constructed with US$70million or 1,357 percent over budget. Undoubtedly, it’s an extreme example. But the fact of the matter is that almost all the mega-construction projects are completed while exceeding 80 percent or more of the planned budget, according to McKinsey stats.
In order to solve this problem, AI is yet again helping the real estate industry. A California-based startup, Doxel offers a solution that utilises the power of AI, LIDAR Imaging and Robotics. The platform captures the construction sites’ 3D images with the help of autonomous robots. These images are then fed to AI algorithms that analyse this data and convert it into valuable insights. It helps the project managers and engineers immediately react to any current and upcoming issues on time. The results that this platform offers are incredibly promising and effective, allowing project managers to save up to 11 percent of the planned budget.
Such platforms usually use Artificial Neural Networks which not only predicts the possible cost overrun but also allow managers to save from their planned budget. The most common historical data and factors that these neural networks use are:
Project size
Contract type
The competence level of working teams
Start and end dates of the project
AI systems can also help the staff to enhance their knowledge and skills quickly by remotely accessing training materials. Not only does it reduce the time, but it also cuts the chances of budget overrun.
Artificial Intelligence Enables Efficient Mortgage Lending
Mortgage lending is one of the biggest parts of the real estate industry, and it is data-intensive by definition. A bank requires documents such as proof of income, credit history and bank statements to offer people a shot at mortgage lending.
For both banks and customers, this process can be very time-consuming. The customers need to obtain all the documents, and the lenders also need time to process and analyse all that data. Additionally, there must not be a single mistake while processing and analysing this data because of the astronomical prices of property.
In order to manage this problem, the mortgage lending sector has been using the OCR (Optical Character Recognition) technique for decades. It can read and analyse data automatically from the documents that borrowers provide. However, like many other technologies it comes with one big limitation. The documents that can only be used for OCR must be in a specific format to come up with accurate data insights. If the documents are not in the necessary format, then the solution won’t be able to provide useful results – and most of the documents are not in that format. That’s why human input is currently necessary to validate the results OCR provides.
On the other hand, machine learning techniques and solutions are able to provide more accurate and informative results. Human interference is also negligible, and that’s why more and more lenders are acquiring AI for mortgage lending. According to an estimate, the AI-based solutions provide results that are three times more accurate than earlier methods. An AI-based solution to analyse borrower documents is actually a combination of both OCE and machine learning tools. Not only do these solutions allow lenders to reduce their staffing costs, but they also save time for both parties.
A solution that uses both ML and OCR is now usually called Capture 2.0, and it’s just a matter of time before it becomes the industry standard.
Property recommendations based on customer preferences
Not all of the customers know the definition of a perfect property, and many can’t choose from the range of available options. It’s usually very challenging for customers to select the right option according to their unique needs when it comes to renting, selling or buying real estate.
AI technology solves this problem by analysing customer preferences and providing the most suited available options. The property recommendation engines have already become a reality. They work on the same principles as the product recommendation engines do, such as Amazon Personalise. In the real estate sector, these solutions provide customers with the most suited property on the basis of real-time analysis; such as customers’ previous interactions, preferences and purchases. Not only does it help customers find the right property options, but it also helps businesses to increase their sales.
