Entity matching at scale


Go to NumFOCUS academy page.

Entity matching is the process of finding records in one or more data sources that refer to the same entity. This talk will discuss a scalable Entity Matching technique that addresses some of the critical challenges such as significantly different names being used to refer to the same entity and highly skewed frequency distributions as well as various tricks of the trade.


Lorraine D’almeida

Data science professional with sharp business acumen and a strong passion for analytics, programming and artificial intelligence. Have extensive technical experience with formulating hypotheses, designing simple and complex machine learning algorithms to solve real problems, and putting models in production.