You are here:

How to Maximize Major Gifts With Machine Learning

Posted Mar 04, 2021 03:25 PM
Believe it or not, 88% of nonprofits’ revenue comes from the top 12% of their donors. This top tier of donors are those who contribute “major gifts.”

While the definition of “major” depends on the size and scope of your organization, it’s universal that nonprofits put a substantial amount of effort into seeking out and cultivating major gifts—considering the potential donation sizes that major gifts represent, it only makes sense to dedicate effort to obtaining them.

Machine learning—an aspect of artificial intelligence used in some nonprofit software programs—can do wonders for your major gift outreach program, in part because of advanced  data analytics and self-correcting, predictive models. Machine learning can shift the burden of extensive prospect research from your team to your computers, opening up more time for you to do the more human aspects of running a nonprofit—building relationships with donors, advocating for change, and working toward your mission.

This article provides an introduction to the concept of machine learning for nonprofits and presents the two major ways machine learning tools can jump start your major gift outreach efforts. You'll learn:

  • What is "machine learning?"
  • How can machine learning maximize major gifts?

Even one additional major gift can make a huge difference for your nonprofit’s goals for the year. Let’s get into how machine learning can help you get there!

What is machine learning?

While the term “machine learning” may draw to mind robots and sci-fi movies, it’s actually relatively commonplace these days.

The term refers to the ability of computers to improve their algorithms based on their experience. Computers “learn” how to make their models more accurate, precise, and predictive, leading to increased usefulness for the users running the programs. When your Netflix account suggests specific titles for you to watch based on your viewing history, it’s a product of machine learning. This means the algorithm that leads to the suggested titles is constantly being updated—every time you stream a new show or movie! Machine learning is considered to be a subset of artificial intelligence.

In the nonprofit space, machine learning can be used to draw useful insights about your donors and predict their behavior for the future.

Nonprofit fundraising software like DonorSearch can integrate with your donor database and automatically perform research to inform its machine-learning models and make predictions about donors’ future behavior. This means your team doesn’t have to conduct any of the tedious research. With algorithms constantly updating based on new data, you can extract the most useful information from your donor database with machine-learning powered models.

Now that you know the basics of machine learning, let’s dive into how exactly it can help your nonprofit secure more major gifts.

How can machine learning maximize major gifts?

In order to use machine learning to maximize your major gifts, your nonprofit will first need a robust set of data. Without that input, any machine learning models you attempt to run won’t have sufficient information to formulate predictions and improve their algorithms. So make sure your donor database is thorough, complete, and hygienic.

Machine learning can evaluate prospects’ potential gift capacities

When nonprofits attempt to find out information about potential donors that may indicate whether or not they would donate and how much they could feasibly contribute, it’s called prospect research.

Prospect research is an essential aspect of major gift fundraising, as it can tell you where to look for major gifts. That way, you can aim your donor recruitment and stewardship efforts toward donors who have a high likelihood of actually donating a significant amount, thereby saving your team time and effort on the way to achieving your fundraising goals.

As part of your organization’s effort to conduct prospect research, your prospects’ capacity to give is an important metric to determine. Machine learning can analyze a variety of data points to optimize your ability to predict a donor’s potential gift capacity. Many of these data points are called wealth indicators.

Wealth Indicators

Wealth indicators are publicly available data points about donors that provide insight into their income and wealth status. Wealth screening technology can seek out these records and compile important information for your organization. Using these indicators, you’re better able to estimate the size of a potential gift one of your prospects might make so that your fundraising asks will be more specific and personalized.

Wealth indicators can tell you which of your prospects is financially capable of making a major gift and the likely size of that gift. Some of the major wealth indicators include:

  • Political contributions. If a supporter has made a donation to a political campaign or cause in the past, that could indicate they’d be willing to make a donation to support your cause as well. It’s important to note the size of the political contributions. Larger political gifts tend to indicate the supporter is more well-off financially and capable of spending significant amounts of money on causes like yours.
  • Stock ownership. Another publicly accessible wealth indicator is whether or not the supporter owns stocks. Stock ownership—especially high-value stocks—is a strong indicator of wealth and suggests that the supporter may have more income to spend on philanthropic causes.
  • Real estate holdings. Many wealthy people own real estate. According to DonorSearch’s wealth screening guide, supporters who own $2 million or more in real estate are 17 times more likely to donate to a philanthropic cause than the average person. It can be helpful to understand your supporters’ real estate portfolios as they can provide insights into their financial position. The value of their real estate assets could suggest the scale of gift they would be able to donate to your cause.

Machine learning tools can take all of these indicators in and generate a "capacity to give score" that can inform your major donor fundraising efforts going forward.

Machine learning can predict prospects’ likelihood to give.

Perhaps the most useful aspect of machine learning tools for your nonprofit’s fundraising and development team is their ability to predict prospects’ likelihood to give. Likelihood to give is based on wealth indicators as previously mentioned, plus a second category: philanthropic indicators.

Philanthropic Indicators

Philanthropic indicators provide information about the type of causes prospects are drawn to and what their passions are. Philanthropic indicators can tell you how likely your cause/messaging/story is to resonate with the prospect and lead to a donation. Philanthropic indicators include:

  • Past volunteer experience. If a prospect has volunteered with any philanthropic organization in the past, at the very least you can conclude that they have some level of interest in philanthropy, however small. More specifically, you can look at the types of nonprofits the prospect has volunteered for to get an idea of the causes they support. If they volunteered to help further similar missions to yours, that may be a good sign that they’d be willing to contribute to your cause, financially or otherwise.
  • Past contributions to your nonprofit. The first donation a major donor makes is not often a major gift. Usually, once you’ve cultivated a new donor, they start out at smaller donation tiers and increase their gifts over time as their relationship with your organization grows. Analyzing the supporter’s past contributions can tell you not only if the donor would be likely to give again, but also the approximate major gift size they’d be willing to contribute.
  • Contributions to other organizations. If you’re able to determine that a prospective donor contributes to other organizations with similar missions to yours, that could indicate they would be willing to make a donation to your organization as well. After all, many donors are attached to the mission, not the specific nonprofit working to accomplish it.
  • Nonprofit board involvement. If a prospect has served on a nonprofit’s board of directors, that’s an indicator that they have a significant interest in that nonprofit’s mission. If that mission is similar to your organization’s, it would increase the likelihood of that supporter making a major contribution to your nonprofit.
  • Personal connection to your cause. If you’re able to understand a little bit about your prospect’s personal lives, you may glean some insights into what kind of causes they would be likely to support. For example, a prospect with a family member with a known medical issue might want to contribute to support research into curing their disease.
  • All of these philanthropic indicators can be considered by a machine learning program and used to estimate the prospect’s affinity to give. "Affinity to give" describes the likelihood of the prospect to make a major contribution out of interest in your cause or mission. (If you need a brush up on affinity to give or would just like some more information on the topic, check out this article.)

Now, affinity to give and capacity to give can be analyzed jointly by a machine learning model to produce a single, important metric: likelihood to give, which integrates wealth and philanthropic indicators into one holistic, informative predictor of giving.

Such information about prospective donors is invaluable as you decide where to allocate outreach resources in your efforts to steward major donors. Once you’ve secured your major donors, make sure to track important major gift metrics to continue to gain insight into your major gifts program. DNL OmniMedia’s list of major gift metrics can point you in the right direction when it comes to choosing key performance indicators (KPIs) to track.

Machine learning models have the remarkable ability to take a breadth of different factors into account when advising you on major donor fundraising and stewardship. Sifting through wealth indicators and philanthropic indicators, your machine learning models will continuously provide you with better and better predictions on where to focus your efforts. You’ll be well on your way to meeting all of your major gift targets. Good luck!

About the Author

Sarah Tedesco is the Executive Vice President of DonorSearch, a prospect research and wealth screening company that focuses on proven philanthropy. Sarah is responsible for managing the production and customer support department concerning client contract fulfillment, increasing retention rate and customer satisfaction.

She collaborates with other team members on a variety of issues including sales, marketing and product development ideas.