Personalizing Intervention Probabilities By Pooling
This work addresses the challenge of personalizing intervention timing in mobile health, though it is incremental in improving prediction methods.
The paper tackled the problem of predicting future context occurrences for mobile health interventions to optimize treatment delivery, finding that pooling data across users reduces error rates compared to personalized and batch methods.
In many mobile health interventions, treatments should only be delivered in a particular context, for example when a user is currently stressed, walking or sedentary. Even in an optimal context, concerns about user burden can restrict which treatments are sent. To diffuse the treatment delivery over times when a user is in a desired context, it is critical to predict the future number of times the context will occur. The focus of this paper is on whether personalization can improve predictions in these settings. Though the variance between individuals' behavioral patterns suggest that personalization should be useful, the amount of individual-level data limits its capabilities. Thus, we investigate several methods which pool data across users to overcome these deficiencies and find that pooling lowers the overall error rate relative to both personalized and batch approaches.