05:50 AM

Property Managers Gain Greater Predictive Power to Help Further Decrease Future Evictions

TransUnion launches ResidentScore 3.0, an enhanced analytics screening model for the rental industry

Evicting a resident comes at great cost to both the renter and property manager. In fact, about 4% of rental properties result in an eviction at an average cost of $5,000 per unit for the property manager. To better assist property managers to ensure they get the highest quality renters in appropriate units, TransUnion (NYSE: TRU) launched today its ResidentScore 3.0 proprietary scoring model.

The enhanced solution was unveiled at TransUnion's Annual Property Management Summit in Chicago, attended by 100+ multifamily senior executives. Leveraging artificial intelligence enabled machine learning, the rental housing-specific score is built on actual multi-family outcomes data to offer property managers greater insight into predicting the likelihood a renter will be evicted or “skip” out of their rental unit without paying within 12 months.

“Property management companies can face significant losses when evictions are high. With screening as the gateway to all things that occur on a property, the best way to identify which applicants may pose a risk is to have a more efficient and effective process in place for vetting potential residents,” said Maitri Johnson, vice president of multifamily at TransUnion. “Having the proper checks and balances in place to reduce costly involuntary turnover can lead to huge savings.”

ResidentScore 3.0 is the third generation of TransUnion’s artificial intelligence based multi-family score that has been in the market since 2013, becoming the industry leading solution for determining the likelihood of eviction or adverse rental outcome. The score ranges from 350-850 with a higher score indicating a lower expected rate of eviction. ResidentScore 3.0 is 4% more predictive than the previous model, and outperforms standard credit models by 16%.

Compared to common industry practices, ResidentScore 3.0 draws a more accurate prediction of renter outcomes by leveraging multiple variables and new data elements. The custom models utilize machine-learning technology, rendering a decision in 60 seconds or less, so property managers may detect a larger percentage of higher-risk renters at the time of application. As a result, property managers can better differentiate good residents from high-risk renters and better predict an individuals’ risk of evictions and skips.

Lower ResidentScores = Higher Expected Eviction Rates


12 Month Expected Bad Rate















*12 Month Expected Bad Rate: The percentage of residents within a designated score range that will either be evicted or skip out owing money in the first 12 months.

“Every renter has a story and taking a ‘one-size-fits-all’ approach to scoring applicants does not provide property managers with the necessary insight to determine the good residents from those who may have a propensity for skipping out,” added Johnson. “ResidentScore 3.0 fills that void in the marketplace by leveraging robust data and analytic capabilities and presenting a more holistic view of each renter.”

Learn more about ResidentScore 3.0 by registering for the Oct. 10 webinar, “Get in the Know on ResidentScore 3.0”, or by visiting

About TransUnion (NYSE: TRU)

Information is a powerful thing. At TransUnion, we realize that. We are dedicated to finding innovative ways information can be used to help individuals make better and smarter decisions. We help uncover unique stories, trends and insights behind each data point, using historical information as well as alternative data sources. This allows a variety of markets and businesses to better manage risk and consumers to better manage their credit, personal information and identity. Today, TransUnion has a global presence in more than 30 countries and a leading presence in several international markets across North America, Africa, Europe, Latin America and Asia. Through the power of information, TransUnion is working to build stronger economies and families and safer communities worldwide.

We call this Information for Good