Skip to main content

Table 8 Results of blocking methods for dataset-C

From: A proficient cost reduction framework for de-duplication of records in data integration

Blocking method

Single key blocking (SKB)

Composite blocking key (CKB)

Multipass blocking (MPB)

Blocking keys

SDX

SB4

SB3

SDX

SB4

SB3

SDX

SB4

SB3

Record comparisons

3639

4175

10678

249

583

986

4348

5340

15652

Matches

542

848

956

231

551

755

719

1008

1030

F-Score

0.675

0.886

0.939

0.358

0.684

0.831

0.805

0.970

0.970