PORTALE DELLA DIDATTICA

Ricerca CERCA
  KEYWORD

Development of tools to detect dataset bias

keywords ARTIFICIAL INTELLIGENCE, AUTOMATED DECISION MAKING, DATA BIAS, DATA ETHICS, FAIR MACHINE LEARNING

Reference persons JUAN CARLOS DE MARTIN, ANTONIO VETRO'

Research Groups Centro Nexa su Internet & SocietÓ, DAUIN - GR-16 - SOFTWARE ENGINEERING GROUP - SOFTENG, DAUIN - GR-22 - Nexa Center for Internet & Society - NEXA

Description Automated decision-making (ADM) systems may affect multiple aspects of our lives. In par- ticular they can result in systematic discrimination of specific population groups, in violation of the EU Charter of Fundamental Rights. One of the potential causes of discriminative be- havior, i.e. unfairness, lies in the quality of the data used to train such ADM systems.
Using a data quality measurement approach combined with risk management, both defined in ISO standards, the work focuses on balance characteristic to understand how balance of protected attributes in training data can be used to assess the risk of unfairness and discimination in ADM systems.


See also  2021-bal-giq.pdf  https://avetro.polito.it/authorsversion/journals/2021-bal-giq.pdf

Required skills Good knowledge of data analysis techniques and tools , R or python


Deadline 30/06/2022      PROPONI LA TUA CANDIDATURA




© Politecnico di Torino
Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY
Contatti