Not always a black box: Machine learning approaches for model explainability

This is a past event

98 people went

Location image of event venue

Details

Speaker: Violeta Misheva, Ph.D., Data Scientist at ABN AMRO Bank N.V.
https://www.linkedin.com/in/violeta-misheva-phd-29674588/

Topic:
Not always a black box: Machine learning approaches for model explainability

Schedule:
6:00pm - 6:30pm - ODSC Intro, Pizza & Refreshments
6:30pm - 7:20pm - Talk
7:20pm - 7:30pm - Q&A
7:30pm - 8:00pm - Networking

Bio:
Violeta has been working as a data scientist at ABN AMRO bank for the past 2 years. Before that she worked as a data science consultant at Accenture, the Netherlands for about 1,5 years. Before working in the industry, Violeta was working in academia. She completed a Ph.D. degree from Erasmus University in the field of applied econometrics.

Abstract:
Most data scientists will agree that in most cases, a more complex model will result in a more accurate model. However, this can result in less reliability of the model, or less trust that business stakeholders have within it. In this talk, we will review some approaches to explainability, go into details of one concrete model, and summarize a use case where that model was used.

ODSC Links:
• Get free access to more talks like this at LearnAI:
https://learnai.odsc.com/
• Facebook: https://www.facebook.com/OPENDATASCI/
• Twitter: https://twitter.com/odsc & @odsc
• LinkedIn: https://www.linkedin.com/company/open-data-science/
• West Conference Oct 29 - Nov 1: https://odsc.com/california
• Europe Conference Nov 19 - 22: https://odsc.com/london