Applied Machine Learning with Python: Donor Upgrade Targeting

Track: Data Analytics Symposium

Session Number: 2042
Date: Wed, Jul 31st, 2019
Time: 10:30 AM - 12:00 PM
Room: Grand Saguaro South

Description:

In this session, you will learn how to build a classification model in python to help identify constituents that you could target for giving level upgrades. By determining what features distinguish donors who upgraded to a gift club level in last year, you can then find other similar constituents to reach out to for upgrades this year.

We will discuss feature engineering in SQL, data exploration in Tableau, step through an example analysis using python and scikit-learn in a jupyter notebook, and show some example dashboards that could be used to monitor outcomes. Resources for learning these topics will also be provided.

In addition to the technical walk-through, we will also discuss some potential challenges related to predictive modeling in general, and classification models in particular, and give tips on how you could implement a similar project at your institution.
Session Type: Breakout Session (90min)

Primary Competency: DA:Competency 1: The Data Science Umbrella
Secondary Competency: DA:Competency 4: Statistical Techniques and Competencies
Tertiary Competency: DA:Competency 5: Visualization/Reporting Techniques and Competencies
Intended Audience Level: Level I, Level II
Recommended Prerequisites: This talk will be geared toward people who have at least done some prior work with advancement datasets, such as report development. Though I will be showing code during my presentation, no coding experience is necessary in order to grasp the overall concepts. I will explain the machine learning/predictive modeling process.
Learning Objective #1: Attendees will learn how python machine learning and predictive modeling techniques can be applied to identify constituents most likely to take an action, such as giving at a high enough level to become a gift club member.
Learning Objective #2: Attendees will learn common challenges and pitfalls related to applying machine learning to answer advancement questions.
Shop Size: Small
Session Type: Breakout Session (90min)

Primary Competency: DA:Competency 1: The Data Science Umbrella
Secondary Competency: DA:Competency 4: Statistical Techniques and Competencies
Tertiary Competency: DA:Competency 5: Visualization/Reporting Techniques and Competencies
Intended Audience Level: Level I, Level II
Recommended Prerequisites: This talk will be geared toward people who have at least done some prior work with advancement datasets, such as report development. Though I will be showing code during my presentation, no coding experience is necessary in order to grasp the overall concepts. I will explain the machine learning/predictive modeling process.
Learning Objective #1: Attendees will learn how python machine learning and predictive modeling techniques can be applied to identify constituents most likely to take an action, such as giving at a high enough level to become a gift club member.
Learning Objective #2: Attendees will learn common challenges and pitfalls related to applying machine learning to answer advancement questions.
Shop Size: Small