Dev Conference by Neo4j
Session Track: Data Science
Session Time:
Session description
Entity Resolution (ER) serves to interlink fragmented and dispersed data, facilitating the identification of records representing identical real-world entities. This function is pivotal for intelligence analysis, enriching investigations by ensuring comprehensive and uniform data merging. This session will showcase a robust end-to-end approach for precise and effective data consolidation, adaptable to batch or incremental processing and predominantly reliant on graphs. Key themes will encompass customizable similarity rules, harnessing node attributes and relationship patterns, and strategic utilization of Neo4j indexes and GDS. Additionally, we’ll delve into diverse data modeling strategies, evaluating their advantages and drawbacks and how to accommodate dynamic data changes.
Data Scientist, GraphAware
Federica is a Junior Data Scientist at GraphAware. She holds a master's degree in Mathematics from University of Salento, where she wrote a thesis on data streaming. She is passionate about Machine Learning and Deep Learning, particularly natural language processing, and enjoys data modeling and data querying. With a creative approach, she has already gained experience in these fields with small-scale projects.
