This document discusses predicting medication adherence through predictive modeling. It begins by outlining the problem of medication non-adherence and its impacts. It then describes the methodology used, which involved blending data from Medicare, drug information databases, and census data to derive predictors and classify patients based on adherence. Regression and decision tree models with 45 predictors were able to predict medication adherence days and classify patients as adherent or non-adherent. The inferences from the models supported the hypothesis that public health, personal, and medication factors influence non-adherence. The document concludes by discussing interventions like behavioral, financial, and clinical approaches that can be tailored to individuals to improve adherence.