Fairness in Machine Learning: are you sure there is no bias in your predictions?


Nowadays, Machine learning (ML) is used to predict nearly everything: from houses price to future criminals. Often, decisions based on ML systems have a significant impact on our life: they influence recruiters who evaluate our CV or banks that should grant us a loan. However, can we trust these systems and be sure that their predictions are fairly computed? What if a bias in the training data is amplified by these systems leading to unequal decisions? In the talk we will understand how to identify such biases and mitigate their effects.

Language: English

Level: Intermediate

Azzurra Ragone

Innovation and transformation lead - EY

I love to transform enterprises and bring them to the future. Currently, I am Innovation and Transformation lead for EY Business Solution. I worked for Google as a Program Manager in the Developer Relations team, for BurdaForward as Branch Manager and for Exprivia S.p.A as a Project Manager and BI consultant for various Italian companies (Generali, Eni, Telecom). Former research fellow in AI and Machine Learning for many years, I worked as a researcher manager for several years at the Polytechnic of Bari, the University of Trento, the University of Michigan and the University of Milan Bicocca

Go to speaker's detail