Iterative Partial Fulfillment of Counterfactual Explanations: Benefits and Risks

Counterfactual (CF) explanations, also known as contrastive explanations and recourses, are popular for explaining machine learning model predictions in high-stakes domains. For a subject that receives a negative model prediction (e.g., mortgage application denial), they are similar instances but with positive predictions, which informs the subject of ways to improve. Various properties of CF explanations have been studied, such as validity, feasibility and stability. In this paper, we contribute a novel aspect: their behaviors under iterative partial fulfillment (IPF). Specifically, upon receiving a CF explanation, the subject may only partially fulfills it before requesting a new prediction with a new explanation, and repeat until the prediction is positive. Such partial fulfillment could be due to the subject's limited capability (e.g., can only pay down two out of four credit card accounts at this moment) or an attempt to take the chance (e.g., betting that a monthly salary increase of \$800 is enough even though \$1,000 is recommended). Does such iterative partial fulfillment increase or decrease the total cost of improvement incurred by the subject? We first propose a mathematical formalization of IPF and then demonstrate, both theoretically and empirically, that different CF algorithms exhibit vastly different behaviors under IPF and hence different effects on the subject's welfare, warranting this factor to be considered in the studies of CF algorithms. We discuss implications of our observations and give several directions for future work.