Multipurpose synthetic population for policy applications

Jiri Hradec (jiri.hradec@ec.europa.eu), Massimo Craglia, Margherita Di Leo, Sarah de Nigris (sarah.de-nigris@ec.europa.eu), Nicole Ostlaender (nicole.ostlaender@ec.europa.eu) and Nicholas Nicholson (nicholas.nicholson@ec.europa.eu)
Additional contact information
Jiri Hradec: European Commission - JRC, https://joint-research-centre.ec.europa.eu/index_en
Massimo Craglia: European Commission - JRC, https://joint-research-centre.ec.europa.eu/index_en
Margherita Di Leo: European Commission - JRC, https://joint-research-centre.ec.europa.eu/index_en
Sarah de Nigris: European Commission - JRC, https://joint-research-centre.ec.europa.eu/index_en
Nicole Ostlaender: European Commission - JRC, https://joint-research-centre.ec.europa.eu/index_en
Nicholas Nicholson: European Commission - JRC, https://joint-research-centre.ec.europa.eu/index_en

No JRC128595, JRC Research Reports from Joint Research Centre

Abstract: While privacy preservation is a major topic today, until recently, striking the balance between usefulness and detail in data was achieved by aggregation on linear scale. New methods for handling analytics however allow to close this gap and to preserve both privacy and knowledge. Compared to other privacy-preservation techniques, synthetic data can have the best value/effort performance. Synthetic population models facilitate application of novel methods for data-driven policy formulation and evaluation, representing a unique opportunity. This report showcases several applications of structured population such as population activity-based modelling, knock-on effects of selective lock-downs during the COVID-19 pandemic, investigative analysis of existing policy instrument design in the energy transition domain, and applications for synthetic cancer patient records. The text carefully weighs pros and cons of synthetic data in these policy applications to provide actionable insights for decision makers on opportunities and reliability of advice based on synthetic data. Such data can become unifying bridge between policy support computational models, provide data hidden in silos, and become the key enabler of artificial intelligence in business and policy applications in Europe. Synthetic data have potential help controlling unevenness and bias in algorithmic governance and enable better targeted policies with small regulatory footprint.

Keywords: synthetic data; synthetic populations; data for artificial intelligence; new polices; integration; big data; activity-based modelling (search for similar items in EconPapers)
Date: 2022-06
New Economics Papers: this item is included in nep-big
References: Add references at CitEc
Citations:

Downloads: (external link)
https://publications.jrc.ec.europa.eu/repository/handle/JRC128595 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ipt:iptwpa:jrc128595

Access Statistics for this paper

More papers in JRC Research Reports from Joint Research Centre Contact information at EDIRC.
Bibliographic data for series maintained by Publication Officer (jrc-dir-b-publications@ec.europa.eu).