This document discusses how advanced analytics and predictive modeling can help associations achieve strategic goals. It contrasts business intelligence with data science and explains how predictive modeling fits within an association's analytics framework. The document also provides examples of predictive models that associations could use, such as models to predict meeting attendance, purchasing likelihood, or long-term revenue from new members. Finally, it discusses how AFP has used predictive analytics to improve initiatives like customer journeys, onboarding programs, and community platforms.
1. The foresight of advanced
analytics
Date: December 14, 2016
Time: 1:45 pm
Galina Kozachenko, Director Strategic Data Analytics, AFP
Kelly Baker, Chief Analytics Officer, Association Analytics
2. What & Why Data Analytics
I never guess. It is a
capital mistake to
theorize before one has
data. Insensibly one
begins to twist facts to
suit theories, instead of
theories to suit facts.
Sir Arthur Conan Doyle,
Author of Sherlock Holmes
stories
3. BI or Data Science?
Business Intelligence Data Science
Deductive Reasoning Inductive & Deductive
Reasoning
Backward Looking Forward-Looking
Slice and Dice Data Interact with Data
Warehoused & Silo-ed Data Distributed, Real Time Data
Analyze the Past, Guess
the Future
Predict & Advise
Creates Reports Creates Data Products
Analytic Output Answer & Create
Questions. Provides
Actionable Answers.
6. Data Analytics must align with Strategy
Is what you are trying to
explain going to help you
achieve your strategic goals?
Is insight being delivered
to the right people at the
right time?
How do you embed data
analytics into your
organization strategy?
8. AFP – Discover and Embed
Data
Discovery/
Visualization
Recommendations
Key insights
Data
Collection
Domain
Knowledge
Strategic
Roadmap
Business
Stakeholders
12. - Segmentation
- Marketing plan
- Strategy
alignment
- Execution
- A/B testing
- Collect
data
- Feed back
into the
model
From deployment to evaluation
14. Segmentation & Marketing Plan
Identified 4 segments (key business drivers channels)
Marketing plan – engage 90 days before renewal and 60 days after
Conference Channel 1, 2, 3, 4
Certified Email 1, 2, 3, 4
Certification Channel 1, 2, 3, 4
Membership Channel 1, 2, 3, 4
Email 5 (All four groups get this same email)
19. Snowball effect – community platform
Selection + Implementation (with SSO) - 60 days
20. Snow ball effect - onboarding
DAY
1
DAY
3
DAY
7
DAY
10
DAY
17
DAY
24
DAY
31
Netforum
Welcome
MM
Welcome
Collaborate
Welcome
MM
Community
MM
Get Involved
MM
Content
Collaborate
Update Bio
Collaborate
Intro Yourself
Collaborate
Login & Browse
Collaborate
Upload Pic
DAY
38
DAY
45
DAY
52
DAY
59
MM
Career Development
DAY
90
MM
New Member Survey
DAY
275
MM
Renewal
21. Snowball effect – tell a story with Marketing
Automation
• Closer partnership Marketing+Data Analytics
• Re-designed automation
• Feed results from one into another
27. Associations and predictive analytics
• Meeting Attendance Model to predict which members will attend an
upcoming meeting
• Decision Tree to visually show how different paths affect conversion
times.
• Interactive Tool created from a regression model that helps
individuals see how different decisions will impact outcomes.
• 20-Year Revenue Model that calculates net present value of a new
member and thus total membership revenue -- including what-if
scenarios from simulation results for each variable.
• Purchasing likelihood Model to predict whether/when an individual
or company will purchase an item.
28. “If you can’t explain it simply, you
don’t understand it well enough.”
- Albert Einstein, Physicist