pgch predictive analytics for planned giving - …c.ymcdn.com/sites/ · predictive analytics for...

37
Predictive Analytics for Planned Giving Josh Birkholz Bentz Whaley Flessner

Upload: duongtuong

Post on 01-May-2018

218 views

Category:

Documents


4 download

TRANSCRIPT

Predictive Analytics for Planned Giving

Josh BirkholzBentz Whaley Flessner

What Is “Analytics?”

L ki B k L ki F dLooking Back• Constituents• Program

Looking Forward• Constituents• Program• Program • Program

Suddenly cool

2

Setting the stage

3

Fundraising Has Three Primary Business Processes

Base DevelopmentOne to many strategies of engagementOne-to-many strategies of engagement

Major/Planned Gift DevelopmentOne to one high ROI strategiesOne-to-one high ROI strategies

Prospect DevelopmentC i f b jConversion from base to major

Prospect Development has Three Stages Feeding Major and Planned Gift Cultivation

Market ResearchIdentification with screening and modeling

Prospect ResearchQualification with data

Fi ld R hField ResearchDiscovery / qualification

through interaction

Plan Strategy

Stewardship CultivationMajor Gift

FundraisingCycle

5Solicitation

Effective Prospect Development for Planned Giving

Identifies prospects meeting the criteria planned gift donors.Traditional characteristics- Traditional characteristics

- Characteristics unique to your organizations

Works with fundraisers to develop strategies for aligning the p g g gprospects with the institution for a philanthropic partnership.

Characteristics

AssumptionsC i t t d

ObservationsA ti ll Consistent donors

Old donors

Donors with appreciated

Assumptions generally accurate for most institutions.

Other common characteristics Donors with appreciated assets from our research:

Legacy families

Multiple property owners

Employment in education d bli iand public service

Donor loyalty

Positive donor experience

7

Positive donor experience

How is Loyalty Achieved?

Needs Needs met consistently

Loyalty+ =consistently

Introducing Predictive Analytics

9

Distinction Predictive Analytics Distinction

over Cl ifi i

y

Classification

10

Drawing Planned Giving Donors Out of a Hat

Imagine a hat with 130 slips of paper.

About 31% of the slips have the words “planned giving donor” written on them.

If you draw a slip out of the hat If you draw a slip out of the hat, approximately 1 in 3 will be a PG donor.

For most organizations, planned giving donors represent a far lesser portion (<5%).

Can We Improve This Ratio?

We could survey our actual planned giving donors asking:donors asking:

How would you describe yourself?- A blue slip of paperp p p- A green slip of paper- A yellow slip of paper

Survey ResultsNow Which Slip of Paper Will You Select?

If You Choose Blue…

Will you draw a l d i i planned giving

donor on average 1 out of 2 times?

The Answer: Unknown

There is not enough information.

Y d t k th di t ib ti f th d l tiYou do not know the distribution of the random population.

15

Consider Your View

Now, which slip will you select?

Population Total Count % of Total PG Donors % of PG

Donors% of Color that are PG Donors

Blue 60 46% 20 50% 33%

Green 60 46% 12 30% 20%

Yellow 10 8% 8 20% 80%

Total 130 100% 40 100% 31%Total 130 100% 40 100% 31%

33%33%

67%

1 in 3 1 in 5 4 in 5

Principle

Common characteristics may not be distinguishingcharacteristicscharacteristics.

How populations are different (target vs. random) is more interesting statistically and predictive than common characteristics of a target group.

17

Modeling Can Predict Many Things

Major, planned, and annual giving

Bequests, annuities, trusts

Program or department models. (giving to fine arts capital needs (giving to fine arts, capital needs, scholarships, patient care, etc.)

Membership likelihoodS i k b i iSeason ticket subscriptionsAlumni affinityChannel preferences (mail Channel preferences (mail, phone, email)Next gift amounts

18

Loyalty scoring with precise weightings

Effective for Planned Giving:

Your constituents compared to

Your success stories using

Your data to identify

Your unique opportunity

19

How is it accomplished?

20

Method

Understand your goals before you begin.y g

Gather your data. Included demographics, giving, research, and screening dataand screening data.

Prepare the data for modeling.

Model.Model.

Evaluate the results against existing donors and prospects.

Score the file and implement the results.

21

Common Score Format (Fractional ranking displayed)

All records have a ranking and a 0–1,000 score.

Planned Giving Rank Label

Planned Giving Score

Minimum Maximum

0 Lower 50% 4 500

1 Top 50% 500 750

2 Top 25% 750 900

3 Top 10% 900 9503 Top 10% 900 950

4 Top 5% 950 975

5 Top 2.5% 975 990

6 Top 1% 990 995

7 Top 0.5% 995 997

8 Top 0.25% 998 999

9 Top 0.1% 999 1,000

22

Evaluate by Comparing Scores to Actual PG Donors

90100

5060708090

enta

ge

010203040

Perc

e

0

0 Lo

wer

50%

1 To

p 50

%

2 To

p 25

%

3 To

p 10

%

4 To

p 5%

5 To

p 2.

5%

6 To

p 1%

Top

0.5%

p 0.

25%

p 0.

1%

5

7 T

8 To

p

9 To

p

PG Donor Not PG Donor

23

PG Donor Not PG Donor

Categorize Variables From Output

Giving

DemographicsGeography

Management

Capacity

24

Sample of Possible Variables in Your Model

Category Variable

Giving

Length of Giving Relationship

Frequency Index

Monthly Payment PreferenceMonthly Payment Preference

Capacity Multiple Property Ownership

>100 miles from campus

Geography Texas (-)

77251 (+)

Event Attendance (+)

Management Survey Response (+)

Alumni Volunteer(+)

Ed J b T l ( )Demographics

Education Job Title(+)

Single(+)

25

Opportunity: Review Portfolio, Prioritize Direct Marketing Appeals, g pp

Planned Giving Not Assigned a Model Rank Prospect Manager Managed

0 Lower 50% 53,425 92

1 Top 50% 26,507 257

2 Top 25% 15,330 724

3 Top 10% 4,767 585

4 T 5% 2 201 4744 Top 5% 2,201 474

5 Top 2.5% 1,197 410

6 Top 1% 326 208

7 Top 0.5% 129 139

8 Top 0.25% 59 101

9 Top 0 1% 20 88

26

9 Top 0.1% 20 88

Bringing Data Mining In-House

27

Bringing Data Mining In-House

More and more organizations have in house data mining have in-house data mining capacity, from large shops to small shops.

Large shops generally have dedicated staff.

S ll h h d l d h Small shops have developed the skill sets in research, advancement services, or annual giving.

28

Making the Case

Gather references of peers and aspirant peers.

B ild f ti l j t tBuild a cross-functional project team.

Start with short-term projects—specific appeals.- Communicate goals before the projectCommunicate goals before the project.- Communicate the success after the project.

Educational and research institutions:- Explore on-campus knowledge resources (economics, statistics,

business departments).Explore on campus software resources- Explore on-campus software resources.

29

Statistics Software

SPSS- My personal preferencey p p- User friendly for expert and novice alike- Large network of other researchers using SPSS

SASSAS- Very powerful for large data sets- Needed for regulatory testing

(not necessary in fundraising)(not necessary in fundraising)- Good network of researchers using SAS

DataDeskObj t i t d f t t d t d- Object-oriented format easy to understand

- Excellent for exploratory analysis- Large network of other researchers using DataDesk

30

Training

Software training courses

Conferences and users groups

Learning through outsourcing (you b i th d l ll are buying methodology as well

as analysis)

Onsite consultingOnsite consulting

Campus resources

31

Learn Through Outsourcing

Many organizations outsource their analytics; benefits include:benefits include:

Expert analysis.

Opportunity to learn from their methodologyOpportunity to learn from their methodology.

High level of service over the short term.

32

Developing In-House Capacities

It is not hard to learn.

A l ti i b i t f th tit t l ti d Analytics is becoming part of the constituent relations and admissions skill set.

Nobody knows your data like you do.y y y

Ability to create multiple models and analysis—not to be restricted by costs.

33

Final Thoughts

34

When You Leave Today, Remember:

Build a prospecting plan around your unique characteristicsyour unique characteristics.

Consider predictive analytics to identify and prioritize your list.

Comparing PG donors to random donors is more valuable than summarizing common PG donor summarizing common PG donor characteristics.

Whether you outsource or build yanalytics in-house, analytics is within your reach.

35

Questions?Questions?

Joshua BirkholzP i i l B Wh l FlPrincipal, Bentz Whaley Flessner

Founder of DonorCast

89646:JMB:abl:050410.

7251 Ohms Lane Minneapolis, Minnesota 55439ph: 952-921-0111 fax: 952-921-0109

[email protected] www.donorcast.com