HOW DOES DATAGRID AI DETERMINE BUYER SCORES?
The purpose of the Buyer Score is to help you identify and locate the prospects who are most likely to buy from you.
HERE’S HOW WE ACCOMPLISH THAT USING MACHINE LEARNING:
First, we analyze data from thousands of customers within your industry.
The AI combs through all of these records and looks at hundreds of specific data points for each record, such as
customer income
home value
age
owner/renter status
property type
home equity
number of bedrooms
net worth
ect
The system analyzes all of these records in order to identify patterns in buyer behavior.
It may discover, for example, that if somebody has a home value over $500,000, they are three times more likely to buy from you.
That information will now play a vital role in a prospect’s Buyer Score.
After recognizing dozens of these patterns, the AI can accurately identify the type of prospect that is most likely to buy from you.
It can then analyze individual homeowner information and tell you how closely that person matches your ideal prospect. The AI will also continue to learn and optimize as you work, so the longer you use it, the better it will be at finding customers.
HERE’S AN EXAMPLE OF HOW WE GRADE INDIVIDUAL HOMES:
First, we collect homeowner information for all the houses in the location. Then, we compare each one to the ideal buyer profile we’ve developed.
LESS LIKELY TO BUY
POSSIBLE TO BUY
MORE LIKELY TO BUY
IF YOU’RE SELLING SOLAR, FOR EXAMPLE,
IF YOU’RE SELLING SOLAR, FOR EXAMPLE,
then the ideal buyer profile consists of approximately 280 data points, weighted by importance. In this case, some of the most important signifiers that someone will buy solar is the sun number, the year the house was built, the amount of mortgage liability, the number of bedrooms in the home, the total rooms in the home, and the likelihood that the occupant will move in the next few months.
So, the AI modeling will weigh these factors strongly when grading a home. Here’s an example of how this would work for a single home:
The system collects data for a specific house, and learns that it is owned by the Smith family.
The Smith family has lived at their home for the last ten years. Mr. and Mrs. Smith are both in their young 40s. They have three kids and live in a four bedroom home. They have a joint income of $130,000 per year, and have generated significant equity in their home.
Based on what the system has already learned about solar buyers, it will likely give the Smith family a high score, because they align well with ideal buyers within the most significant data points.
Another family who has little equity in a one-bedroom home will rank quite a bit lower by comparison.
Once we’ve created scores for all the homes in a specific area, we can average those scores out and assign a new score to the area as a whole. The size of these scored areas can scale from the neighborhood to state levels. This makes it easier for users to make strategic decisions about area assignments, expansion territories, macro analysis, and more.
Every industry is different and even changes over time. But this dynamic model makes it easy for companies to quickly identify and target their unique ideal buyers so that they don’t have to waste time and resources with people who are unlikely to buy from them.