Identifying leads who are more likely to convert into donors for charities in Australia using machine learning techniques.

Abstract

"This research focuses into enhancing the quality of fundraising at ABC Company by prioritizing potential donors based on data-driven techniques. The Random Forest algorithm was identified as the best-performing model based on sensitivity, specificity, balanced accuracy and AUC Score. The research identified key factors like ""Quiz status"" and ""Email status"" as strong predictors of donation behavior. The model successfully classifies leads into high, medium, and low potential donors. It has provided a targeted approach for maximize conversions and reduce costs. Although some limitations, such as technical issues with R software, prevented the use of certain models like K-Nearest Neighbors (KNN) and Support Vector Machines (SVM), the research achieved its primary objectives. The findings emphasize the effectiveness of machine learning in optimizing donor conversion strategies It highlights the importance of engagement in predicting donor behavior. This approach not only improve the donor conversion rates but also reduces the time and cost involved. This study provides a foundation for future research to refine and expand predictive models in the context of charitable giving."