Optimal Targeting in Fundraising: A Machine-Learning Approach

Optimal Price Targeting

“…Simester et al (2020a) emphasize the value of randomized-by-action instead of randomized-by-policy experiments, and suggest an "off-policy" approach for evaluating the profitability of targeting policies that were not observed in the data. The combination of randomized-by-action experiments and off-policy estimators has also been used by Ascarza (2018), Hitsch and Misra (2018), Yoganarasimhan et al (2020), Yang et al (2020), Cagala et al (2021), and Liu (2022). We contribute to this literature by extending off-policy estimators -specifically inverse probability weighted estimators -to a setting with panel data and non-random treatment assignment of prices.…”

Machine Learning and Fundraising: Applications of Artificial Neural Networks

“…Papers belonging to the first class include, for instance, the contribution [21], with a discussion on how and to what extent Artificial Intelligence could be used in the FR sector. In the second class, one may cite [14], where an MLP and a Support Vector Machine are developed and applied for predicting levels of charitable giving using publicly available data sources, and [9], where Classification and Regression Decision Trees, and Classification Random Forests are used for detecting the so-called net Donors (that is Donors whose expected donation is higher than the marginal FR costs).…”

“…To this end, we initially focused our attention on 2I +1 = 15 different MLPs with a single hidden layer, where I specifies the number of input features, having respectively from 1 to 2I + 1 nodes in the hidden layer itself 9 . Each of these MLPs has been trained using the dataset described in Section 3.1.…”

How causal machine learning can leverage marketing strategies: Assessing and improving the performance of a coupon campaign

“…They find that the total volume of user-generated content and the extent to which user photos are rated as helpful have a significant positive effect on the likelihood of restaurant survival. Another study from the domain of marketing that uses causal ML is Cagala et al [71]. The authors estimate the optimal strategy for distributing gifts among potential donors in a fundraising campaign that maximizes expected net donations.…”