The GraphRAG Manifesto: Unlock Better GenAI Results With Knowledge Graphs | Read Now

Neo4j logo

Nodes2024

Dev Conference by Neo4j

Register for NODES 24

You only need to register once to attend all sessions.

Name Similarity 2.0: Reviewing Sorensen-Dice

Session Track: Data Science

Session Time:

Session description

In the context of identity resolution at LATAM Airlines, the necessity to advance name comparison methods became clear. After several months of employing the Sorensen-Dice algorithm, it was evident that optimization was possible. They then enhanced the algorithm with more realistic, name-based modifications. This session will provide a detailed comparison and the outcomes of this enhancement process. Attendees will gain insights into the challenges and solutions in refining name comparison algorithms, learning how these improvements can be applied to boost the accuracy of identity resolution.

Speakers

photo of Mauricio Genta

Mauricio Genta

Data Scientist, LATAM Airlines

Mauricio Genta is a mathematics grounded data scientist/engineer, who tries to produce value for LATAM Airlines using his skills and creativity.

photo of Bruno Matonte

Bruno Matonte

Data Scientist, LATAM Airlines

Data scientist with an atmospheric sciences background tackling entity resolution problems.