The success of machine learning algorithms in a wide range of industries and domains has led to a desire to leverage their power in ever more areas. To drive adoption and gain a deeper understanding of what the model has learned, explainability is top of mind for the machine learning community. Explanations also help manage ethical, legal, and business risks.
Maren Eckhoff discusses modern XAI approaches that increase the transparency of black box algorithms by providing explanations for each prediction made. Many of these methods can be applied to any model, including tree ensembles and neural networks, without limiting their performance. Join in to explore techniques and open source implementations, illustrated with real-world examples.
Maren Eckhoff is a principal data scientist at QuantumBlack, where she leads the analytics work on client projects, working across industries on predictive, explanatory, and optimization problems. Her role includes defining the analytical approach, developing the code base, building models, and communicating the results. Maren also leads the technical training program for QuantumBlackâs data science team and arranges bespoke trainings, seminars, and conference attendance. Previously, Maren worked in demand forecasting. She holds a PhD in probability theory from the University of Bath.
For exhibition and sponsorship opportunities, email strataconf@oreilly.com
For information on trade opportunities with O'Reilly conferences, email partners@oreilly.com
View a complete list of Strata Data Conference contacts
©2019, O’Reilly UK Ltd • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • confreg@oreilly.com