US 11,734,612 B2
Obtaining a generated dataset with a predetermined bias for evaluating algorithmic fairness of a machine learning model
Sérgio Gabriel Pontes Jesus, Gondomar (PT); Duarte Miguel Rodrigues dos Santos Marques Alves, Lisbon (PT); José Maria Pereira Rosa Correia Pombal, Lisbon (PT); André Miguel Ferreira Da Cruz, Vila do Conde (PT); Joäo António Sobral Leite Veiga, Lisbon (PT); Joäo Guilherme Simöes Bravo Ferreira, Lisbon (PT); Catarina Garcia Belém, Seixal (PT); Marco Oliveira Pena Sampaio, Vila Nova de Gaia (PT); Pedro Dos Santos Saleiro, Lisbon (PT); and Pedro Gustavo Santos Rodrigues Bizarro, Lisbon (PT)
Assigned to Feedzai—Consultadoria e Inovação Tecnológica S.A.
Filed by Feedzai—Consultadoria e Inovação Tecnológica, S.A., Coimbra (PT)
Filed on Jun. 30, 2022, as Appl. No. 17/855,323.
Claims priority of provisional application 63/237,961, filed on Aug. 27, 2021.
Claims priority of application No. 22175664 (EP), filed on May 26, 2022.
Prior Publication US 2023/0074606 A1, Mar. 9, 2023
Int. Cl. G06N 20/00 (2019.01)
CPC G06N 20/00 (2019.01) 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving an input dataset;
generating an anonymized reconstructed dataset based at least on the input dataset wherein the generated dataset includes tabular data;
introducing a predetermined bias into the generated dataset while training a generative adversarial network (GAN) model, wherein:
the generative adversarial network model is configured to append one or more columns to the generated dataset, the one or more columns including at least one dataset attribute or attribute of interest for fairness evaluation; and
a generative adversarial network sampler is configured to randomly sample the generated dataset appended with the one or more columns;
forming an evaluation dataset based at least on the generated dataset with the predetermined bias; and
outputting the evaluation dataset for evaluating algorithmic fairness.