This work proposes Dynamic Linear Epsilon-Greedy, a novel contextual multi-armed bandit algorithm that can adaptively assign personalized content to users while enabling unbiased statistical analysis. Traditional A/B testing and reinforcement learning approaches have trade-offs between empirical investigation and maximal impact on users. Our…

This paper describes and evaluates a computerized system, MATCH, which is being used in South Carolina to match or link student records from year to year. The functioning of MATCH and its specific features are described, and its use in matching student test scores is detailed. The problem of mismatched records and the use of visual editing to…