Record linkage (entity resolution or de-deduplication) is the process of merging noisy databases to remove duplicate entities. While record linkage removes duplicate entities from the data, many researchers are interested in performing inference, prediction or post-linkage analysis on the linked data, which we call the downstream task. Depending on the downstream task, one may wish to find the most representative record before performing the post-linkage analysis. Motivated by the downstream task, we propose first performing record linkage using a Bayesian model and then choosing representative records through prototyping. Given the information about the representative records, we then explore two downstream tasks - linear regression and binary classification via logistic regression. In addition, we explore how error propagation occurs in both of these settings. We provide thorough empirical studies for our proposed methodology, and conclude with a discussion of practical insights into our work.
Download