C1 (2 points)
https://knobit.org/id/task/rmd-match-quality/C1
Also as Turtle · JSON-LD · RDF/XML
| dcterms:license | https://creativecommons.org/licenses/by/4.0/ |
|---|---|
| owl:sameAs | https://bitbucket.org/reffa/ontology/id/task/rmd-match-quality/C1 |
| rdfs:label | C1 (2 points) en |
| schema:hasPart | rmd-match-quality C1: agreement weights log2(m/u) instead of equal weights |
| schema:hasPart | rmd-match-quality C1: disagreement weights log2((1-m)/(1-u)) instead of zero |
| schema:identifier | C1 |
| schema:position | 1 |
| schema:text | Field weights, 1 each. (a) The draft gives every field the same agreement weight (+6) whatever its m and u: each compared field's agreement weight is log2(m/u) - first_name 5.00, surname 6.52, postcode 7.32, phone 7.00 (date_of_birth 12.00 where compared), ±0.15 - so a field whose values many people share counts for less. (b) The draft scores a disagreement 0, the same as a missing value: each compared field's disagreement weight is log2((1-m)/(1-u)) - first_name -4.60, surname -3.63, postcode -3.05, phone -1.47 (date_of_birth -5.64), ±0.15 - and missing stays 0. en |