Machine learning with fully anonymized data

Adam Drake (@aadrake)

Abstract

Sharing data for any purposes, including for machine learning, is fraught with problems related to ethics, organizational policy and dynamics, and regulatory restrictions.  In this talk I will discuss the topic of feature hashing and how, with a slight modification from the standard approach, we can satisfy many ethical and other requirements by training our models without any knowledge of the underlying data.  In addition to presenting the ethical and regulatory benefits of building machine learning models using completely anonymized data, if time permits we may explore and discuss the performance characteristics and benefits of such an approach.

Bio (also available at https://aadrake.com/press.html):

Adam Drake’s professional background includes a wide range of technical professional and management roles, including: leading technical business transformations in global and multi-cultural environments, performing in-depth technical due-diligence and funding analysis for investors, and mentoring new technical and operational executives. His passion is to help companies become more productive by improving internal leadership capabilities, and accelerating product development through technology and data architecture guidance. His technical interests include online learning systems, high-frequency/low-latency data processing systems, recommender systems, distributed systems, and functional programming.

Adam has a background in Applied Mathematics and has worked in technology roles since the 90s. His career spans a variety of industries, including e-commerce, online travel, online marketing, financial services, healthcare, and oil and gas.

LinkedIn: https://linkedin.com/in/aadrake

Website: https://aadrake.com

Twitter: https://twitter.com/aadrake

About #miToronto

Both audiences, those who are interested in machine intelligence / data science, and those who are practitioners of machine intelligence / data science are invited, and can both expect to learn something new.

Attendees can expect to learn what machine intelligence is, its applications, and what’s going on in Toronto’s data science community. Significant getting to know you time, and Q&A time is deliberately set aside.

MARS AUDITORIUM, DOWNSTAIRS, near the Tim Horton’s, use the glass doors (the unmarked wood ones are all locked).

Back to all