TY - JOUR
T1 - Behavior based record linkage
AU - Yakout, Mohamed
AU - Elmagarmid, Ahmed K.
AU - Elmeleegy, Hazem
AU - Ouzzani, Mourad
AU - Qi, Alan
PY - 2010/9
Y1 - 2010/9
N2 - In this paper, we present a new record linkage approach that uses entity behavior to decide if potentially different entities are in fact the same. An entity's behavior is extracted from a transaction log that records the actions of this entity with respect to a given data source. The core of our approach is a technique that merges the behavior of two possible matched entities and computes the gain in recognizing behavior patterns as their matching score. The idea is that if we obtain a well recognized behavior after merge, then most likely, the original two behaviors belong to the same entity as the behavior becomes more complete after the merge. We present the necessary algorithms to model entities' behavior and compute a matching score for them. To improve the computational efficiency of our approach, we precede the actual matching phase with a fast candidate generation that uses a "quick and dirty" matching method. Extensive experiments on real data show that our approach can significantly enhance record linkage quality while being practical for large transaction logs.
AB - In this paper, we present a new record linkage approach that uses entity behavior to decide if potentially different entities are in fact the same. An entity's behavior is extracted from a transaction log that records the actions of this entity with respect to a given data source. The core of our approach is a technique that merges the behavior of two possible matched entities and computes the gain in recognizing behavior patterns as their matching score. The idea is that if we obtain a well recognized behavior after merge, then most likely, the original two behaviors belong to the same entity as the behavior becomes more complete after the merge. We present the necessary algorithms to model entities' behavior and compute a matching score for them. To improve the computational efficiency of our approach, we precede the actual matching phase with a fast candidate generation that uses a "quick and dirty" matching method. Extensive experiments on real data show that our approach can significantly enhance record linkage quality while being practical for large transaction logs.
UR - http://www.scopus.com/inward/record.url?scp=84856597650&partnerID=8YFLogxK
U2 - 10.14778/1920841.1920899
DO - 10.14778/1920841.1920899
M3 - Article
AN - SCOPUS:84856597650
SN - 2150-8097
VL - 3
SP - 439
EP - 448
JO - Proceedings of the VLDB Endowment
JF - Proceedings of the VLDB Endowment
IS - 1
ER -