Spoiled for Choice? Personalized Recommendation for Healthcare Decisions: A Multiarmed Bandit Approach

Choice overload is a common problem in many online settings, including healthcare. Online healthcare platforms tend to provide large variety of behavior intervention information or programs help individuals modify their lifestyles improve wellness. However, having too options can significantly increase searching cost, prevent users from discovering the truly relevant interventions, and harm users’ long-term decision-making efficiency. This motivates us propose personalized recommendation system tailored support for individuals’ participation. The proposed framework, deep-learning diversity-enhanced multiarmed bandit (DLDE-MAB), integrates several predictive prescriptive analytics components combat unique challenges presented setting. It leverages machine learning adaptive real-time support, theory-guided diversity promotion scheme cover multiple needs, deep further enhance dynamic context representation. Through extensive experiments, we show that framework outperforms various competing models terms its adaptivity data dynamics, diversity, uncertainty. model evaluation results important implications business intelligence personalized, contextualized, agile decision making.