Data linkage: techniques, challenges and applications

Workshop theme

The overall aim of the programme is to bring together researchers and practitioners from various research disciplines and application domains to foster exchange between different parts of the mathematical sciences where the topics of data linkage and anonymisation are being addressed, as well as between researchers investigating data linkage and privacy protection. These topics have so far often been considered separately. This aim of the programme is quite different from other very topic and domain specific INI programmes.

With this in mind, the objective of this second workshop on data linkage is to strongly encourage interaction between participants from different disciplines, to facilitate cross-disciplinary learning, and to set an agenda of the big challenges in the area of data linkage. Topics to be covered and discussed will range from computational and statistical aspects of data linkage, to privacy and confidentiality, and application case-studies and examples.

To encourage cross-disciplinary interactions, besides invited presentations by world leading researchers and practitioners in data linkage, there will to be several interactive sessions that follow a "speed-dating" approach where participants in short pair-wise discussions present to each other their background and interests, and issues and challenges they see in the area of data linkage from their perspective. The key ideas and challenges will then be synthesised on the last workshop day with the aim of producing an interdisciplinary position / state-of-play / call for action / great challenges paper. This paper is to be refined by key workshop participants and the workshop organisers into a potentially full journal article after the workshop. Some of the identified challenges and problems will be worked on during the remainder of the main programme.

We group the workshop topics into five (computational aspects, statistical aspects, privacy and confidentiality, research applications, and industry/government applications), and begin the workshop with presentations by leading international experts to set the scene.

We also plan to have a practical "Hackathon" directly following the workshop (Thursday 15th and Friday 16th September) to allow interested participants to collaborate on solving some of the challenges identified in the workshop by developing initial prototypes or fleshing out research directions.

Applications for this workshop are now closed

The Institute kindly requests that any papers published as a result of this programme’s activities are credited as such. Please acknowledge the support of the Institute in your paper using the following text:

The author(s) would like to thank the Isaac Newton Institute for Mathematical Sciences, Cambridge, for support and hospitality during the programme Data linkage: techniques, challenges and applications, where work on this paper was undertaken. This work was supported by EPSRC grant EP/K032208/1.

Timetable

Monday 12th September 2016
09:00 to 09:50	Registration	No Room Required
09:50 to 10:00	Welcome from Christie Marr (INI Deputy Director)	Room 1
10:00 to 11:00	Rainer Schnell City University, London; Universität Duisburg-Essen Hardening Bloom Filter PPRL by modifying identifier encodings	Room 1
11:00 to 11:30	Morning Coffee	No Room Required
11:30 to 12:00	Gerrit Bloothooft Universiteit Utrecht Historical life cycle reconstruction by indexing	Room 1
12:00 to 12:30	Patrick Ball Human Rights Data Analysis Group Deduplicating databases of deaths in war: advances in adaptive blocking, pairwise classification, and clustering	Room 1
12:30 to 13:30	Lunch @ Wolfson Court	No Room Required
13:30 to 14:30	Bill Winkler U.S. Census Bureau Computational Methods for Linking Sets of National Files	Room 1
14:30 to 15:30	Amy O'Hara U.S. Census Bureau The U.S. Census Bureau’s Linkage Infrastructure: Overview and New Challenges	Room 1
15:30 to 16:00	Afternoon Tea	No Room Required
16:00 to 17:00	Intra-disciplinary “speed-dating”	Room 1
16:00 to 17:00	'speed-dating' sessions	Discussion Room
17:00 to 18:00	Welcome Wine Reception & Poster Session at INI	No Room Required

Tuesday 13th September 2016
09:30 to 10:00	Hye-Chung Kum Texas A&M University; UNC Chapel Hill and RIMS Privacy Preserving Interactive Record Linkage (PPIRL)	Room 1
10:00 to 10:30	James Boyd Technical Challenges associated with record linkage	Room 1
10:30 to 11:00	Evan Roberts University of Minnesota Record linkage with complete-count historical census data	Room 1
11:00 to 11:30	Morning Coffee	No Room Required
11:30 to 12:00	Bradley Malin A LifeCycle Model for Privacy Preserving Record Linkage	Room 1
12:00 to 12:30	Luiza Antonie University of Guelph Tracking people over time in 19th century Canada: Challenges, Bias and Results	Room 1
12:30 to 13:30	Lunch @ Wolfson Court	No Room Required
13:30 to 14:00	Katie Harron London School of Hygiene and Tropical Medicine Handling identifier error rate variation in data linkage of large administrative data sources	Room 1
14:00 to 14:30	Ruth Gilbert University College London GUILD: GUidance for Information about Linked Datasets	Room 1
14:30 to 15:00	Dinusha Vatsalan Australian National University Advanced Techniques for Privacy-Preserving Linking of Multiple Large Databases	Room 1
15:00 to 15:30	Harvey Goldstein University of Bristol; University College London A scaling approach to record linkage	Room 1
15:30 to 16:00	Afternoon Tea	No Room Required
16:00 to 17:00	'speed-dating' sessions	Discussion Room
16:00 to 17:00	Intra-disciplinary “speed-dating”	Room 1

Wednesday 14th September 2016
09:00 to 10:00	Erhard Rahm Universität Leipzig Big data integration: challenges and new approaches	Room 1
10:00 to 10:30	Vassilios Verykios Hellenic Open University Space Embedding of Records for Privacy Preserving Linkage	Room 1
10:30 to 11:00	Andy Boyd University of Bristol ‘Data Safe Havens’ as a framework to support record linkage in observational studies: evidence from the Project to Enhance ALSPAC through Record Linkage (PEARL).	Room 1
11:00 to 11:30	Morning Coffee	No Room Required
11:30 to 12:00	Mauricio Sadinle Duke University A Bayesian Partitioning Approach to Duplicate Detection and Record Linkage	Room 1
12:00 to 12:30	Changyu Dong University of Strathclyde From Private Set Intersection to Private Record Linkage	Room 1
12:30 to 13:30	Lunch @ Wolfson Court	No Room Required
13:30 to 15:30	Discipline based discussion and synthesis of workshop outcomes: a few paragraphs per discipline (manifesto)	Room 1
15:30 to 16:00	Afternoon Tea	No Room Required
16:00 to 17:00	Presentation and discussion of findings; synthesis of findings; workshop closure	Room 1
19:30 to 22:00	Formal Dinner at Emmanuel College	No Room Required

Thursday 15th September 2016
09:00 to 17:00	Hackathon / Zeeland challenge	Room 1
11:00 to 11:30	Morning Coffee	No Room Required
12:30 to 13:30	Lunch @ Wolfson Court	No Room Required
15:30 to 16:00	Afternoon Tea	No Room Required