Date of Award
Doctor of Philosophy (PhD)
Department of Educational Administration and Foundations: Educational Administration
Institutions of higher education can benefit from using predictive modeling and data mining techniques to enhance capital and fundraising campaigns to yield higher levels of financial contributions. The purpose of this study was to enhance the sophistication of alumni fundraising by using predictive modeling and data mining techniques to address: (a) What factors are most likely to predict the likelihood of alumni making a financial contribution, and (b) What factors are most significant in predicting the amount of money alumni will contribute. Among the 17 variables used by this study those of significance for predicting the likelihood to give included: distance from alma mater, event attendance, volunteer status, degree year, and life stage. Additionally, the linear regression model predicting the amount of a first time gift accurately predicted over 50% of individual giving at the lowest of three donation levels.
Walcott, Mark, "Predictive Modeling And Alumni Fundraising In Higher Education" (2014). Theses and Dissertations. 285.
Imported from ProQuest WALCOTT_ilstu_0092E_10356.pdf