ACIS 2024 Proceedings

Abstract

This study investigates the factors influencing the success of charitable fundraising campaigns on GoFundMe, emphasizing the role of interaction features. Six machine learning models (KNN, Logistic Regression, SVM, ANN, Decision Tree, AdaBoost) were used to evaluate feature predictive power. Combining interaction features with project information significantly enhanced accuracy, with Logistic Regression and AdaBoost achieving perfect AUC scores of 1.00. Decision Tree results across 18 project categories demonstrated that integrating interaction features improved predictive outcomes, especially for Business, Charity, and Memorial fundraisers, achieving AUC scores of 0.86, 0.81, and 0.88, respectively. These findings highlight the importance of donor interactions in boosting campaign success. This research provides actionable insights for charitable organizations to optimize their fundraising strategies and increase donor engagement, ultimately maximizing the impact of their campaigns.

Download

Share

COinS