Fig. 1From: CIDACS-RL: a novel indexing search and scoring-based record linkage system for huge datasets with high accuracy and scalabilityCIDACS-RL Architecture. In the first step the dataset A is indexed. During the query step, each record in dataset B is used to retrieve the N most similar records in the index and store them in a logical dataset (candidates). Finally, in the query step, a custom comparison method is applied to classify the candidate pairsBack to article page