A Tutorial on Techniques for Scalable Privacy-preserving Record Linkage

Large amounts of data are being collected both by organisations in the private and public sectors, as well as by individuals Much of these data are about people, or they are generated by people Financial, shopping, and travel transactions Electronic health and financial records Tax, social security, and census records Emails, tweets, SMSs, blog posts, etc. Analysing (mining) such data can provide huge benefits to businesses and governments October 2013 – p. 2/101 Motivation (continued) Often data from different sources need to be integrated and linked To improve data quality To enrich data with additional information To allow data analyses that are impossible on individual databases Lack of unique entity identifiers means that linking is often based on personal information When databases are linked across organisations, maintaining privacy and confidentiality is vital This is where privacy-preserving record linkage (PPRL) can help October 2013 – p. 3/101 Motivating example: Health surveillance (1