Probabilistic Record Linkage and Deduplication after Indexing, Blocking, and Filtering.
Jared S. MurrayPublished in: J. Priv. Confidentiality (2015)
Keyphrases
- record linkage
- data cleaning
- privacy preserving
- multiple databases
- entity resolution
- duplicate detection
- pre filtering
- linked data
- census data
- approximate matching
- information retrieval
- group membership
- database
- bayesian networks
- filtering algorithm
- generative model
- probabilistic model
- case study
- data sets
- posterior probability
- information extraction
- data analysis
- disclosure risk
- data mining