An exploration of algorithmic discrimination in data and classification
This addresses fairness issues in machine learning for stakeholders concerned with ethical AI, but it appears incremental as it builds on existing discrimination analysis.
The paper investigates algorithmic discrimination in predictive systems, analyzing its relationships with classification, data partitioning, and decision models, and demonstrates using real-world data that discrimination in data sets and classification models can be independent.
Algorithmic discrimination is an important aspect when data is used for predictive purposes. This paper analyzes the relationships between discrimination and classification, data set partitioning, and decision models, as well as correlation. The paper uses real world data sets to demonstrate the existence of discrimination and the independence between the discrimination of data sets and the discrimination of classification models.