This technical report, produced in partnership by the Council for Advancement and Support of Education (CASE) and SPSS Inc., explores the promise of data mining alumni records at educational institutions. Working with individual alumni records from The Johns Hopkins Zanvyl Krieger School of Arts and Sciences, a predictive regression model is developed based on commonly-collected variables and a ten-step model-building and testing process. The resulting model's wider applicability is tested successfully on datasets from nine other educational institutions in the United States, Canada, and Europe. Analysis reveals four distinct patterns of giving by alumni. Fundraisers will benefit from this work by using the model to generate predictive scores identifying prospects in their own alumni databases, likely to make a major gift as well as appreciating their own institutions' pattern of giving when making strategic fundraising decisions. A table detailing the aggregated study results is appended. [This report was produced jointly with SPSS Inc.]