Hybrid Record Linkage

Principal Investigator(s):  View help for Principal Investigator(s) Mahin Ramezani, Texas A&M University; Hye-Chung Kum, Texas A&M University; Population Informatics Lab

Version:  View help for Version V2

Published:  View help for Published Date May 04, 2021

Citation

Project Citation: 

Ramezani, Mahin, Kum, Hye-Chung , and Population Informatics Lab. Hybrid Record Linkage. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2021-05-04. https://doi.org/10.3886/E133881V2

Persistent URL:  http://doi.org/10.3886/E133881V2

Project Description

Project Title:  View help for Project Title Hybrid Record Linkage
Summary:  View help for Summary Our Hybrid Record Linkage framework combines the automatic and manual review process to achieve both scalability and high-quality linkage results by allowing the automated algorithms to resolve the majority of the linkages that have a high probability of being either a match or non-match, but also have the option to send ambiguous pairs to human experts for final determination to improve the linkage quality. You can use our trained models to conduct record linkage on your data or train a new model using your own dataset.
Original Distribution URL:  View help for Original Distribution URL https://github.com/pinformatics/hybridRL_code_and_models

Scope of Project

Subject Terms:  View help for Subject Terms Record Linkage; patient matching; machine learning; deduplication; entity resolution


Name Size File Type Download/
Preview
Download this project

Published Versions

V2 [2021-05-04]

V1 [2021-03-03]

Export Metadata

OAI-PMH

DDI 2.5

Report a Problem

Found a serious problem with the data, such as disclosure risk or copyrighted content? Let us know.

This material is distributed exactly as it arrived from the data depositor. ICPSR has not checked or processed this material. Users should consult the investigator(s) if further information is desired.