Predicting Donations from a Cohort Group of Donors to Charities

Abstract

Charity fundraising organizers increasingly attempt to predict the donations to their causes to maximize the effectiveness of their expenditures and achieve their “social good” objectives. Much of the scholarly work in cause-related fundraising uses organization-specific demographic, geographic, psychographic and behavioral information about its donors to forecast donation amounts. Instead of distinguishing the potential donors, this study focuses on the prediction of the donations from existing donors. Specifically, a large dataset containing four years worth of transactional, appeals, source, and donor data related to a leading U.S. charitable organization was made available to the authors by the Direct Marketing Educational Foundation. The current paper contributes to the literature on donor lifetime value by documenting, in the context of a case study, the results of seven models for predicting future contributions using historic data over four years related to the cohort group of acquired donors.