Recommending Dream Jobs in a Biased Real World10/06/2017 Objective: Guidance Machine learning models learn what we teach them to learn. Recommendation systems trained on biased data may reflect the bias. Reducing biases, from societal bias e.g. professional gender gap, to bias introduced by data collection or modeling, is crucial to successfully recommending dream jobs to hundreds of millions members worldwide while being true to LinkedIn vision: To create economic opportunity for every member of the global workforce. Speaker(s)
|