Actionable Recourse via GANs for Mobile Health
This work addresses the need for stakeholders in mobile health to have agency over predictions, though it appears incremental as it applies existing GAN methods to a new domain.
The paper tackled the problem of providing actionable recourse for mobile health apps by using GANs to generate counterfactuals that modify user predictions, demonstrating feasibility on a dataset from the Safe Delivery App with ensemble-survival-analysis-based predictions for medium-term engagement.
Mobile health apps provide a unique means of collecting data that can be used to deliver adaptive interventions.The predicted outcomes considerably influence the selection of such interventions. Recourse via counterfactuals provides tangible mechanisms to modify user predictions. By identifying plausible actions that increase the likelihood of a desired prediction, stakeholders are afforded agency over their predictions. Furthermore, recourse mechanisms enable counterfactual reasoning that can help provide insights into candidates for causal interventional features. We demonstrate the feasibility of GAN-generated recourse for mobile health applications on ensemble-survival-analysis-based prediction of medium-term engagement in the Safe Delivery App, a digital training tool for skilled birth attendants.