Data Science North East: May Meeting

Schedule:

6:00 - food and drinks
6:30 - Diego Schapira
7:00 - Louis Aslett

Main Talk - Louis Aslett - Doing Data Science Blindfolded

Abstract:

There significant concerns surrounding privacy with the growth in storage of private and sensitive data which is to be used in some data science pipeline. This talk will provide an accessible survey of recent results which enable some analyses to be performed on encrypted data in a way which provides security guarantees, even when the analysis is performed in a potentially insecure or untrusted environment (such as a cloud computing platform). We will also cover the pooling of multiple data sources in a way that secures the data and retains privacy of the analysis being performed.

Shorter Talk - Diego Schapira - Tasty NLP with Python

Great location? Friendly staff? Delicious food? Happy Hour??? What are the things that people value or hate the most about their Restaurant
experiences? Using a Yelp dataset of Restaurant Rating & Reviews I will be
playing with popular and not so popular nlp packages in Python focusing
particularly on unsupervised learning techniques to unveil insights from a
large corpus of unstructured data. Very informal but hopefully educative!