When Data Gets Messy: Teaching AI to Think Like a Scientist

There is beauty in messy data. Let's help machines see it too.....
We will dissect together the steps needed to extract relationships in documents. How to standardize messy data in a coherent fashion? How can we increase confidence in machine output? In this session, we will mix coding, with data visualization, and fun analytics examples!
Our presenter tonight is Mahmoud Shobair, PhD. Mahmoud is a data scientist with a background in applied physics, cheminformatics, and human health. He has a passion for end-to-end data science engineering, taking messy data, and transforming it into reliable models in production. His research work focuses on applied machine learning to bridge theory in practice and operationalize models for decision-making. Recently, he has been focusing on how to create data assets, and create value from legacy unstructured data. He holds a Bachelor’s in Physics from the University of Florida, and a PhD in Computational Biophysics and Bioinformatics from the University of North Carolina in Chapel Hill with more than 7 years of R&D experience at the United States Environmental Protection Agency and, presently, Procter & Gamble.