Orateur
Description
Non-profit organizations play a vital role in addressing global challenges, yet their financial sustainability often hinges on the effectiveness of their fundraising campaigns. We collaborate with a major international non-profit organization to develop and test data-driven approaches to increase the efficiency of their fundraising efforts. Our partner organization conducts multiple annually recurring campaigns, which are thematically linked. The short lifespan of individual donors necessitates efficient learning of both the connections between campaigns and response patterns across donors. To this end, we propose two learning algorithms that integrate principles from multi-armed bandits and clustering. We provide theoretical guarantees for these algorithms and validate their performance on real-world data from our partner organization. The results highlight the potential to significantly enhance the organization's fundraising effectiveness.
