MiNDFIRL (MInimum Necessary Disclosure For Interactive Record Linkage) is a prototype software that can be used to enhance confidentiality of datasets by restricting disclosures of identifying information during the record linkage process.
Open Source Code on Git
You can download the open source code here: MiNDFIRL software
From a different project: Our lab has also done some initial work on Machine Learning based automated record linkage codes:
- Machine Learning based (SVM, Random Forest, and neural networks) to link databases in a controlled experiment: AutoRL
- A trained model (based on Random Forest algorithm) for automatic record linkage and and open-source code to apply it to other dataset: Trained Model
- A package to introduce errors into a dataset, enabling us to benchmark record linkage frameworks at different error rates: Error Generator
