Building a Predictive Model: Theory to Application

Track: Data Analytics Symposium

Session Number: 2053
Date: Thu, Aug 1st, 2019
Time: 10:30 AM - 12:00 PM
Room: Grand Saguaro East

Description:

The importance of testing historical assumptions about a donor’s giving likelihood is sometimes underestimated. Organizations that implement predictive modeling as a primary or secondary measure can review their assumptions and build performance benchmarks that better identify which assumptions should be followed. Addressing this need upfront can no doubt be an organizational challenge itself. However, pursuing a path for building a predictive model with little time, experience, and resources is where today’s Prospect Development groups are headed. The Prospect Development team at the University of Missouri has successfully built and implemented such a predictive model and would like to share their successes and failures with the larger community of Prospect Development and Data Analytic practitioners. Furthermore, it helps implement the need for systematically testing those historical assumptions and helping others be aware of associated challenges.
Session Type: Breakout Session (90min)

Primary Competency: DA:Competency 4: Statistical Techniques and Competencies
Secondary Competency: DA:Competency 7: Fundraising Knowledge
Tertiary Competency: DA:Competency 3: Data Manipulation Skills
Intended Audience Level: Level I
Recommended Prerequisites: none
Learning Objective #1: Through discussions about the beginning of our process, attendees will learn what employee resources, employee time, and employee expertise were existing in our team and what we needed to find for iteratively completing our predictive modelling project.
Learning Objective #2: Through discussions about our predictive model, attendees will learn how we selected variables, how we updated our existing affinity formula, and how we structured our implementation with leadership.
Shop Size: Mid-Size/Large
Session Type: Breakout Session (90min)

Primary Competency: DA:Competency 4: Statistical Techniques and Competencies
Secondary Competency: DA:Competency 7: Fundraising Knowledge
Tertiary Competency: DA:Competency 3: Data Manipulation Skills
Intended Audience Level: Level I
Recommended Prerequisites: none
Learning Objective #1: Through discussions about the beginning of our process, attendees will learn what employee resources, employee time, and employee expertise were existing in our team and what we needed to find for iteratively completing our predictive modelling project.
Learning Objective #2: Through discussions about our predictive model, attendees will learn how we selected variables, how we updated our existing affinity formula, and how we structured our implementation with leadership.
Shop Size: Mid-Size/Large