A Recommender System for fund raising management

In fund raising management the use of rigorous mathematical methods and decision support systems has been playing a more and more important role. These techniques develop the classical data base approach proposed by the operational literature. These improvements concern both the mathematical modeling associated with the information management techniques and the specic characteristics of the Associations, with the consequent specializations of the algorithms. In this approach, the role of the potential donors (i.e. contacts) and the process for turning the contacts into actual donors in the context of the so called "giving pyramid" was poorly investigated, despite its high importance in particular from a strategic point of view. In this contribution, we develop a recommender system that uses similarity measures to optimize the contacts' management. This is achieved by a proper use of the information contained in the Association data base, which concern the profiles of those donors that are suitable for the current campaign, and by matching these with the profiles of the contacts by similarity. The similarity among the (normalized) profiles will be realized by a suitable distance-based function. Numerical results show the effectiveness of the proposed approach.