N.Y.U. Mines Personal Data for a Fund-Raising Edge

This New York Times article does not really specify any data mining activities, but it does cover a number of aspects of the prospecting process such as screening, prospect research, peer review, and qualification. Overall, it is an interesting description of prospecting and cultivation work.

The board’s campaign steering committee, made up of trustees, representatives from each N.Y.U. school, a parent representative, and the president of the alumni association, meets about three times a year, and at those meetings Ms. LaMorte also reads names of prospects to the trustees.

Read More

Legacy Admissions and Giving

In many of the models I have built predicting annual and planned giving to universities, multiple alumni relationships within a family is a consistent predictor. Annual and planned gifts tend to be more loyalty-based than investment-based outright major gifts. These relationships are a strong sign of loyalty.

Catherine Rampell, a Princeton senior, discusses the controversial topic of legacy admissions. When a factor is consistently predictive, should there be an emphasis to broaden this factor? If multiple alumni-relationships are predictive of giving, accepting family of alumni over equivalent individuals with no such relationship seems like a natural application. Is this a way to go? Catherine thinks it might not be all bad. She says:

Contrary to popular characterizations, not all alumni are rich, and proponents of legacy preference do not expect a one-to-one financial return for each admit helped by his legacy status, since the school does not tell families whether their legacy status had any effect on their admissions results. But helping out a few alumni kids on the cusp is a benign gesture that can help grease annual giving's wheels nonetheless.

Read more

Marketing to Algorithms

Data mining and modeling is integral to our everyday lives. Many everyday behaviors, conversations, and transactions can be tracked. Max Kalehoff points out in his piece that models need to be much more multidimensional in their approaches. He says:

This concept is terribly important to marketers that must now rebuild their consumer decision-making models. The old linear decision models are becoming irrelevant, and must be replaced with new ones that incorporate not only overt word-of-mouth behaviors, such as face-to-face discussions or online consumer discussions, but all behaviors that create halos of metadata, which algorithms process, mediate and disperse to others.

Read more

Reporting gifts in real time

The folks at the Wikimedia Foundation, which supports Wikipedia and the multi-lingual access to online information, have a great online-gift reporting tool. The Wikimedia Foundation C.O.R.E or Central Online Reporting Engine uses the blog-comment concept as a way to combine community-building, online giving, and gift acknowledgement into one process.

See more

America the Charitable

The CS Monitor revealed some interesting surprises about philanthropy in the USA. Among them is the economic impact. They write:

Charitable giving plays an even larger role in the economy than is suggested by some $260 billion in annual contributions. Each dollar of giving appears to create $19 of extra national income...

Read more

Three Strategies for Successful Data Mining

I would start by establishing the metrics for success. The business understanding should guide the entire project. See my post regarding CRISP-DM.

Which data models are worthwhile? What are the best predictors? Which metrics work? A panel of catalogers and list pros provided simple tactics to help mailers improve the quality of their databases at the “Trick Out Your Data and Kick Up Your Revenue” session held during the List Vision conference earlier this month in New York.

Read more

Generational Giving Habits

Here is a new analysis of generational giving habits. Be sure to read the footnote to the article explaining the $6,000 average.

BOSTON, December 7, 2006 - Baby Boomers report that they will give more to charity in 2006 than in 2005, with average total donations of $6,000. This is the highest level among all generations surveyed and about 20 percent higher than the overall donor average of $5,000, according to a new nationwide survey by the Fidelity® Charitable Gift FundSM 1, which is one of the nation's largest public charities and has the largest donor-advised fund program in the United States.2

Read more

Qualifying New Leads

The most common application of analytics in nonprofit fundraising is for lead generation. Usually, it takes place before research and field qualification (AKA discovery) stages of the process. This article on B2B sales translates well to the discovery process. For many organizations, having an efficient method for connecting with new leads separates the good from the great.

You’ve spent a great deal of time, effort and money putting together your business-to-business sales lead generation programs. How you handle B2B sales leads once you get them makes the difference between a happy sales team and new customers or an unhappy sales team and lost sales.

Read more

Nonprofits Spend Billions to Reach Consumers

Tom Watson of onPhilanthropy discusses nonprofit marketing spending in a recent blog posting.

Never has the world of brands and consumer culture been more closely aligned with philanthropy - and the human desire to change the world for the better. World leaders, captains of industry, rock stars and mega-athletes. They're all embracing philanthropy in the new 21st century, bringing a "win now" mentality to the marketplace, and vowing to see to it that their dollars really do bring about change.

Read more

Why do your donors give to you?

This is an important question every fundraising analytics professional should consider. It is not sufficient to determine who will give to you. We should understand why. I have found that this is rarely one simple answer. Often times, there is a combination of a few predominant types of donors. For example:

• They love you
• They love what you do
• What you do helps them or their business
• They have confidence you will succeed at something they find valuable
• They want to give back (most common self-reported reason--but not always the actual motivator)

The following article provides one example of a giving motivation:

DR. BILL VAN DYK is straightforward about why he serves on the Contra Costa College Foundation board of directors and is now in his second term as its president.
He supports CCC because his San Pablo dental practice is dependent upon graduates from the college's dental assisting program. His personal donations to the CCC Foundation are designated for the dental assisting program, and he urges other West County dentists to follow his lead.

Read More

Why do your donors give to you?

Measuring Corporate Giving

How do we assess the impact of corporate giving? This article from onPhilanthropy discusses new metrics.

"As corporate giving matures within the broader field of corporate social responsibility, so too will the methods by which to measure it. Farron Levy writes that “the quest continues for that elegant, singular equation that measures CSR’s total return on investment.” As individuals and organizations continue to pursue that elusive goal, it is clear that the era of just giving for giving’s sake is over, and a new world of assessing the impact of corporate giving is upon us."

Read More

Top 10 IT Trends for 2007

If your nonprofit fundraising organizations are not pursuing these trends today, they will.

WELLESLEY, MA -- (MARKET WIRE) -- December 05, 2006 -- Nucleus Research today announced its Top 10 IT Predictions for 2007. The annual report has accurately predicted major IT trends for enterprise end users and vendors for the past three years. Nucleus predictions are based on analysis of both vendors and thousands of corporate end-user case studies.

Read More

RFM vs. Predictive Modeling

RFM has long been a measure of customer value. Many nonprofits are using it to describe prospect or donor value. It can be an effective measure for a segment of the donor pool. I have even used the measure as a dependent variable in a linear model to understand the factors and predict future value. In this article from DM News, Melissa Campanelli compares RFM to predictive modeling in a back-to-school campaign.

"Names selected using predictive modeling had a four times higher average monthly spending rate than people selected with RFM, and a three times higher purchase rate. Also, consumers selected with predictive modeling spent 2.5 times more per direct mail piece than those chosen through RFM. "

Read More

CRISP-DM What is it?

Newer people to data mining often ask me about CRISP-DM. They may have heard about it at conferences or from peers. However, as statisticians often do, we assume everyone knows all of the acronyms. In the interest of demystifying data mining for the novice, I will try to provide some basic definitions and resources for common terminology. CRISP-DM is a great place to start. Basically, it is just the standard method for a data mining / predictive modeling project. The letters stand for "CRoss-Industry Standard Process for Data Mining."

"CRISP-DM has not been built in a theoretical, academic manner working from technical principles, nor did elite committees of gurus create it behind closed doors. Both these approaches to developing methodologies have been tried in the past, but have seldom led to practical, successful and widely-adopted standards. CRISP-DM succeeds because it is soundly based on the practical, real-world experience of how people do data mining projects. And in that respect, we are overwhelmingly indebted to the many practitioners who contributed their efforts and their ideas throughout the project."

Read More

Process Analytics

I enjoyed this blog posting by Phil Ayres. Although most of the analytics applications in fundraising are limited to prospecting or direct marketing segmentation, I believe business processes are next. The strong interest in refining performance metrics will lead to descriptive and predictive applications. This will likely start in the deployment of major giving staff. However, managing truly lifelong (yes, even before they graduate higher ed) constituent cycles, and understanding the factors impacting increased engagement will have more sophisticated approaches in years to come.

"In many cases it will make sense for the analytics to focus on purely systems-based business services in the SOA. An example is an online loan customer inquiry. In a call center environment, process analytics would typically focus on attributes like the time to answer, abandon rate, loan value, type of request, all divided by class of customer. In an online world, similar information should be provided to the business to assess the effectiveness of their website, marketing and backend application processing, but the website analytics may not be the place to most manageably gather it, especially since much of the required information would not be exposed at this level."


Read More

Interview with Steve Cone

This MarketingProfs interview with Steve Cone has some great information on branding. Much of this applies well to direct marketing fundraising.

"how you use the Web depends a lot on the type of business you are in and who your audience is. As a general rule, the more affluent the target audience the more attention you should pay to how the Web should be integrated into your marketing campaign. And, for certain, your own Web site must be best in its class."

Read More

Analytics in Political Fundraising

Although it is generally referred to as "microtargeting," data mining has become an effective tactic for political fundraising strategy. In this feature piece about Bloomberg, John Heilemann writes:

What kind of campaign would Sheekey run? He isn’t saying. But judging from the one he devised for Bloomberg in 2005, it would be extremely sophisticated. Schoen points out that Bloomberg’s operation in 2001 was ahead of the Bush team’s now-famous use in 2004 of microtargeting—the new political science of combining consumer-database information with voter rolls to target people likely to be receptive to your message. And in 2005, Sheekey cranked up the tactic up another notch. In both elections, the Bloomberg campaign applied new technology, plus a boatload of cash, to the task of identifying and turning out independent and unenrolled voters. Hence the model that Sheekey would surely try to duplicate on a national scale.

Read more

Analytics in Auction Fundraising

As yet another sign of the strength of analytics in fundraising applications, cMarket is integrating analytics in their online auctions.

cMarket has added an analytics feature to its charity-auction fundraising service for non-profits. cMarket's new SmarterAuction feature draws from data collected from over 1,500 completed cMarket auctions in more than a dozen cause categories to help its nonprofit clients run more successful fundraising auctions.

Click to read more