The method discussed in the present module is intended for matching two data sets on the basis of object characteristics. It is applied in case no object identifiers (of good quality) are available from both datasets. First the potentially matching records in the two data sets are identified. This requires a suitable metric and a cut-off value so that records that are too different are not considered as candidate matches. In the next step from these potential matches, a subset is computed that maximises the number of matches, under suitable constraints. The present module is based on Willenborg and Heerschap (2012). The reader is advised to read the theme module “Micro-Fusion – Object Matching (Record Linkage)” first before reading the present one. The method module “Micro-Fusion – Weighted Matching of Object Characteristics” should also be consulted, as the method described in the present module is a special case of the method discussed there. In particular it contains relevant information on metrics and graphs that are used in the present module.
To read the entire document, please access the pdf file (link under "Related Documents" on the right-hand-side of this page).
Your feedback is appreciated. Please send your remarks, suggestions for improvement, etc. to firstname.lastname@example.org.