A Brock research partnership with a local property management software company has created a data analytics framework that helps landlords and tenants find their perfect match.
The framework is able to capture a segment of the rental market that’s often excluded because of a technicality, says Andrews Moses (MBA ’11), founder and CEO of St. Catharines-based Tenantcube.
“International students and new immigrants are having trouble securing housing because they weren’t in Canada long enough to establish a credit score, so they’re being overlooked,” says Moses.
While Tenantcube already offers a tenant screening service as part of its complete property management platform for landlords and property managers, Moses wanted to find a way around the credit history blockage and increase his clients’ confidence in connecting with suitable renters.
To help achieve these goals, he contacted Brock Professor of Information Systems Anteneh Ayanso, who taught a course Moses completed during his MBA.
“We recognized this as a great opportunity to work together,” says Ayanso. “Since his graduation, Andrews and I have been meeting to discuss his work and ways of expanding his current organization with better data and analytics capability.”
Ayanso approached Master of Science student Shodhanth Ramaswamy and with funding from Mitacs, a nonprofit national research organization, Ramaswamy created a new analytics-driven rental matchmaking service for Tenantcube using a design science approach.
Ramaswamy examined rental sectors in different countries and researched other industry applications that use algorithms — such as those found in the online dating sector — to make recommendations based on particular features.
From that research, he came up with six attributes that, when rated highly, are perceived positively by prospective tenants and landlords, including cleanliness and prompt communication. Users are able to rate the importance of each attribute using a numerical scale.
“The underlying framework is a modified version of a dating algorithm and is designed to continually learn over the course of the product life cycle, allowing us to improve the quality of matches with historical data,” says Ramaswamy.
He says having agreement on a diverse set of criteria can be more effective than relying merely on a credit check.
“The goal of the framework is to characterize tenants and landlords as entities with attributes beyond their ability to borrow and pay their debts,” says Ramaswamy. “By doing so, the framework acts as an intermediary that says, ‘this tenant or landlord would have the characteristics you’d like.’”
Moses says the matchmaking algorithm will ensure long-term success because the emphasis is on cultivating a positive relationship between landlord and tenant.
“You can have the best credit score in the world and be the worst tenant,” he says. “This is a model that can help people make better, wiser decisions backed up by solid data.”
Moses says preliminary results indicate the new system has “great potential for use.” He expects that his company will be using the system by the end of the year.
For Ayanso, support from the funding agency Mitacs enables the team to make a difference beyond the classroom.
“Nothing makes me more excited in research than attempting to solve real problems in society,” says Ayanso. “We plan to expand this project thorough additional funding opportunities and new partnerships.”