Charlotte Rescue Mission

Homeless shelter addresses direct-mail challenges.

How many solicitation letters do you need to mail to reach your fundraising goal? For the Charlotte Rescue Mission, that number is a fraction of what it used to be. In fact, says Tim Troutman, Donor Services Supervisor for Charlotte Rescue Mission, “We enjoy close to a 50 percent increase in responses when we use JMP.”

The Charlotte, North Carolina-based program for homeless men and women uses JMP® software from SAS to target mailings so that they reach the right people for the right programs. Many factors go into consideration to assure that each mailing list includes only those people who are likely to respond to both the type and timing of the solicitation.

“We’d been making decisions based on our own impressions, and now we are using scientific methods,” says Director of Development E.J. Underwood.

Direct mail is the rescue mission’s primary vehicle for soliciting donations. Even though it is the most common marketing tool for homeless shelters, direct mail can be very expensive. “That translates into a higher fundraising cost than a lot of other types of nonprofits,” Underwood says.

And this particular nonprofit is devoted to spending as little as possible on overhead and as much as it can on helping people turn their lives around. Its mission is to help “individuals caught in the cycles of poverty, hopelessness and chemical addiction by meeting their spiritual, physical, emotional, social and vocational needs.”

“We see success as being clean and sober and able to hold a job,” says Underwood. Through two separate facilities – one for men, one for women – 144 people receive shelter and other forms of assistance. Staff members and a slew of medical, educational and community service volunteers work with clients to get them on their feet again. Underwood reports that about 70 percent of the rescue mission’s clients have substance-abuse problems; about one-third suffer from mental illness.

“A lot of people don’t know what we do here,” she explains. “Too many people think we just serve meals.” The organization does serve a lot of meals – about 200,000 a year, in fact. But spreading the word about the entirety of the rescue mission’s work is one of Underwood’s goals for direct-mail campaigns. It’s about helping potential donors understand how the shelter works and how their donations will be put to use.

It’s also about understanding potential contributors and reaching out to them in the most cost-effective way. Explains Underwood: “Whether you’re mailing a six-page newsletter or an invitation to an event, you need to keep costs down and mailing lists clean. Now consider the added pressure of working in the nonprofit world, where the obligation to spend every penny wisely is a heavy burden.”

Troutman uses logistic regression to see which factors contribute to a donor’s response to a solicitation. Troutman recalls that his first models were simple, but got progressively complex as he became more aware of which factors to consider. During his testing processes, the logistic regression models revealed that certain data – life-to-date total amount given, total number of gifts and largest gift amount – was of little or no predictive value. In contrast, certain types of data were found to be very predictive: number of direct-mail gifts, zip code and number of days since the donor’s last gift.

Troutman says his results “have been getting better every month.” With dynamic response models, he figures out who gives as a result of receiving the organization’s newsletter, who will likely give a matching gift in the spring, and who will donate every year at Christmas only, despite additional solicitations at other times of the year.

Before turning to JMP, Troutman and Underwood used an RFM system (standing for recency, frequency and monetary) to manage donor data. The simplistic system, which Troutman described as an “outdated method using outdated technology,” only considered how recently the last donation was made, the total number of gifts and the total gift amount.

In comparison, Troutman’s Logic Regression Response Model (LRRM) considers continuous value of days passed between the last gift and mail date, number of gifts given within the last two years, the average gift amount, the number of gifts given to similar appeals, the number of gifts given at a particular time of year, and the donor’s zip code.

Just by looking at the data in relation to when gifts were given, JMP has enabled more pertinent data to be analyzed. For instance, the old system groups people by their last donation only: one year ago, two years ago, three years ago, etc. “With JMP, it’s a continuous scale,” says Troutman. “If you made a donation 364 days ago, you shouldn’t be in the same category as someone who just gave five days ago. JMP allows us to view all of our data over time – in increments that we select.”

Saving money on direct mail is only part of the equation. Using resources well is an important way to make every penny count. With the goal of understanding how donors react to receiving thank-you calls – or not receiving them – Troutman used JMP to analyze new-donor data. The findings, simplified: People who received thank-you phone calls were much more likely to give a second or third gift to the rescue mission. In fact, “some donors responded extremely well when contacted,” says Troutman. But those very generous gifts came only from the new donors who received calls. The correlation was clear: “Contacting donors not only increases their likelihood to give a second gift, but also had a positive effect on their giving level.” As a result, the organization began seeking out additional people to make the calls and also began recruiting volunteers to help acquire phone numbers for new donors.

Next, Underwood says she wants to use JMP to figure out what parts of the recovery program most greatly contribute to clients’ success – and which ones may relate to failure. By analyzing program data, survey results and exit interviews, she expects to find ways to further improve the program. That, of course, translates to more complete rehabilitations and fewer people who end up back on the streets.

E.J. Underwood and Tim Troutman, Charlotte Rescue Mission

Additional Links

Charlotte Rescue Mission