Fueling innovative software
July 15-18, 2019
Portland, OR

Removing unfair bias in machine learning using open source (sponsored by IBM)

1:30pm3:00pm Tuesday, July 16, 2019
Location: E141/142
Average rating: ****.
(4.00, 3 ratings)

Who is this presentation for?

  • Data scientists, data engineers, and developers interested in learning how to address challenges with bias in data sets and machine learning models




Machine learning models are increasingly being used to make critical decisions that impact people’s lives. However, bias in training data, due to prejudice in labels and under- or oversampling, can result in models with unwanted bias. Discrimination can become an issue when machine learning models place certain privileged groups at systematic advantage and certain unprivileged groups at systematic disadvantage.

Ana Echeverri and Trisha Mahoney walk you through how to use the open source Python package AI Fairness 360, developed by IBM researchers. AI Fairness 360 is a comprehensive open source toolkit that empowers users with the metrics to check for unwanted bias in datasets and machine learning models and state-of-the-art algorithms to mitigate such bias.

You’ll learn which metric is most appropriate for a given use case, and when to use many of the different bias-mitigation algorithms provided in the toolkit. AI Fairness 360 provides an interactive experience as a gentle introduction to the concepts and capabilities of the toolkit for those unfamiliar with Python, as well as detailed tutorials for more advanced data scientists.

This event is sponsored by IBM.

Prerequisite knowledge

  • A basic understanding of machine learning
  • Experience using Python (useful but not required)

Materials or downloads needed in advance

What you'll learn

  • Discover how bias and discrimination can arise within modern machine learning techniques and the methods that can be implemented to tackle those challenges
  • Learn how to evaluate the metrics using the open source AI Fairness 360 toolkit to check for fairness and mitigate machine learning model bias



Ana Maria Echeverri works at IBM focused on Data Science, Machine Learning, and Artificial Intelligence Skills Growth and Strategy. Her career spans multiple leadership roles in Sales, Marketing, Partner Ecosystems, and Analytics in the Technology industry (Informix, Microsoft, Citrix and IBM); and also leadership roles in startups as Founder and as leader in Digital Marketing and Analytics. A lifelong learner, avid reader, and an entrepreneur at heart, her passion is to build from scratch (businesses, strategies, teams, programs) while leveraging data science and AI capabilities and digital competencies. She holds a Computer Engineering degree, an MBA, a Master of Science in Analytics, and a Graduate Certificate in Strategic Management.

Photo of Trisha Mahoney

Trisha Mahoney


Trisha Mahoney is a Technical Evangelist for Machine Learning & AI at IBM. Trisha has spent the last 9 years working in high-tech firms doing product management/marketing roles in AI & Cloud (at IBM, Salesforce, Cisco and Smiths Group). Prior to that, Trisha spent 8 years working as a data scientist in the chemical detection space. She holds an Electrical Engineering degree and an MBA in Technology Management.