Predictive models for charitable giving using machine learning techniques

Abstract

Private giving represents more than three fourths of all U.S. charitable donations, about 2% of total Gross Domestic Product (GDP). Private giving is a significant factor in funding the nonprofit sector of the U.S. economy, which accounts for more than 10% of total GDP. Despite the abundance of data available through tax forms and other sources, it is unclear which factors influence private donation, and a reliable predictive mechanism remains elusive. This study aims to develop predictive models to accurately estimate future charitable giving based on a set of potentially influential factors. We have selected several factors, including unemployment rate, household income, poverty level, population, sex, age, ethnicity, education level, and number of vehicles per household. This study sheds light on the relationship between donation and these variables. We use Stepwise Regression to identify the most influential variables among the available variables, based on which predictive models are developed. Multiple Linear Regression (MLR) and machine learning techniques, including Artificial Neural Networks (ANN) and Support Vector Regression (SVR) are used to develop the predictive models. The results suggest that population, education level, and the amount of charitable giving in the previous year are the most significant, independent variables. We propose three predictive models (MLR, ANN, and SVR) and validate them using 10-fold cross-validation method, then evaluate the performance using 9 different measuring criteria. All three models are capable of predicting the amount of future donations in a given region with good accuracy. Based on the evaluation criteria, using a test data set, ANN outperforms SVR and MLR in predicting the amount of charitable giving in the following year.

A Conceptual Design of an AI-Enabled Decision Support System for Analysing Donor Behaviour in Nonprofit Organisations

“…Attitudes, norms, perceived behavioural control, subjective norms, prior actions, and morals are some elements that influence donor willingness to provide money or volunteer time [9]. Some influential determinants of donor behaviour towards contributing [4], included donor education level, gender, age, population, household income, and ethnicity. ML models (Support Vector Regression, Multiple Linear Regression, Artificial Neural Networks) were created using these criteria to predict future philanthropic giving from donors [5] accurately.…”

“…The findings provide helpful information about NPOs' donor engagement and retentions to donate, as well as donor-recognized profile factors. However, none of the studies mentioned above [4,8,9] attempted to create an AI-enabled DSS for analysing donor behaviour in NPOs. As a result, NPOs lack an AI-enabled DSS for analysing donor behaviour for better decisions making.…”

“…Donors support the goals of NPOs by giving money, gifts, volunteering time, and previous experiences. Private donations are significant in funding NPOs in the USA, which annually contribute to more than 10% of the Gross Domestic Product [4]. Dietz and Keller [5] reported that individuals donate to NPOs because of their deep passion or beliefs about NPOs' needs, attracting around USD 260 billion in 2014 in the USA.…”

“…Dietz and Keller [5] reported that individuals donate to NPOs because of their deep passion or beliefs about NPOs' needs, attracting around USD 260 billion in 2014 in the USA. The factors impacting peoples' intentions towards donating include income, educational level, and previous giving history [4]. Today's NPOs focus on gaining donations by knowing donor behaviour, which requires them to interact with their donors [6] authentically.…”

Optimal Targeting in Fundraising: A Causal Machine-Learning Approach

“…By focusing on effect heterogeneity, we further contribute to a fourth literature strand on heterogeneous responses to fundraising. This literature identifies heterogeneity to (a) characteristics of the charitable organization and the purpose of the charity (e.g., Okten and Weisbrod, 2000;de Vries et al, 2015), (b) characteristics of the donors (e.g., Andreoni et al, 2003;Andreoni and Vesterlund, 2001;Farrokhvar et al, 2018;Rajan et al, 2009;Wiepking and James, 2013), (c) donation motives or preferences of donors (e.g., Bakshy et al, 2012;Harbaugh et al, 2007;Kizilcec et al, 2018), (d) past donation behavior (Schlegelmilch and Diamantopoulos, 1997;Hassell and Monson, 2014), and (e) crowding out (Meer, 2017). Instead of studying single, selected dimensions of heterogeneity, we combine a range of individual characteristics and past donation behavior.…”