fairness-accuracy tradeoff
This Git Repositiory is published in support of the modeling developed for the article "Fairness–accuracy tradeoff: activation function choice in a neural network"
in
AI and Ethics (SpringerNature)
by Michael B. McCarthy & Sundaraparipurnan Narayanan
DOI : 10.1007/s43681-022-00250-9
AIET-D-22-00158R1
Received: 31 October 2022 / Accepted: 6 December 2022
Data sources (From Appendix A):
-
Adult dataset Source: Dua, D. and Graff, C. (2019). UCI Machine Learning Repository. [online] Available at: http://archive.ics.uci.edu/ml/datasets/Adult . Irvine, CA: University of California, School of Information and Computer Science. [Accessed 01 Sept. 2022].
-
French dataset Source: Mabilama, J. M. (2020). E-commerce—Users of a C2C fashion store. [online] Data.world. Available at: https://data.world/jfreex/e-commerce-users-of-a-french-c2c-fashion-store [Accessed 05 Jan. 2022].
For the Neural Networks, data wrangling was completed in Alteryx Designer. Copies of the fully wrangled data are included.
Code (From Appendix B): One Python Notebook for each dataset (two total notebooks) are included in the the respository; both were developed in Google Colab IDE.