This repository details the process of record linkage utilizing machine learning techniques, starting with the generation of synthetic datasets. Initially, synthetic data is created to simulate realistic scenarios and assess linkage models in a controlled environment. Following the validation and refinement of these models, the techniques are deployed on real-world data, enhancing the robustness and accuracy of the record linkage process. This comprehensive approach allows for a thorough evaluation of methods before applying them to actual datasets, ensuring reliable and insightful outcomes in population health research.
-
Notifications
You must be signed in to change notification settings - Fork 0
This repository details the record linkage using machine learning starting with synthetic dataset generation to simulate realistic scenarios. The techniques are then applied to real-world data ensuring robust results. This approach enhances reliability in population health research making it a valuable resource for researchers and practitioners.
tathagatabhattacharjee/Record-Linkage-Using-Machine-Learning-Techniques
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
This repository details the record linkage using machine learning starting with synthetic dataset generation to simulate realistic scenarios. The techniques are then applied to real-world data ensuring robust results. This approach enhances reliability in population health research making it a valuable resource for researchers and practitioners.
Resources
Stars
Watchers
Forks
Packages 0
No packages published