Identifying Indicators of Bias in Data Analysis Using Proportionality and Separability Metrics
Loading...
Authors
Schneider, Madeleine
Grinsell, Jonathan
Russell, Travis
Hickman, Randall
Thomson, Robert
Issue Date
2018
Type
Conference presentations, papers, posters
Language
Keywords
machine learning , bias , separability , proportionality
Alternative Title
Abstract
There have been a number of high-profile cases of artificial intelligence (AI) systems making culturally-inappropriate predictions, mainly due to imbalanced training data and the overall black-box nature of modern deep learning algorithms. In this paper, we consider metrics for analyzing the data to determine the characteristics which may result in a biased model. Specifically, we look at a combination of separability between and proportionality of clusters within a given dataset to identify the presence of implicit biases. We measured the effectiveness of Alpha Diversity, entropy, and euclidean norm as a measure of proportionality. Manually permuting the MNIST and fashion MNIST dataset, we found all three scores strongly correlated with model accuracy. Silhouette scores were used as the separability metric and showed limited but noticeable correlation with predicted accuracy.
Description
Citation
Schneider, Madeleine, Jonathan Grinsell, Travis Russell, Randall Hickman, and Robert Thomson. "Identifying Indicators of Bias in Data Analysis Using Proportionality and Separability Metrics." In International Conference on Social Computing, Behavioral-Cultural Modeling, & Prediction and Behavior Representation in Modeling and Simulation. 2019.
Publisher
SBP-BRiMS Annual Conference