This research seeks to benefit the software engineering society by providing a simple yet effective pre-processing approach to achieve equalized odds fairness in machine learning software. Fairness issues have attracted increasing attention since machine learning software is increasingly used for high-stakes and high-risk decisions. It is the responsibility of all software developers to make their software accountable by ensuring that the machine learning software do not perform differently on different sensitive demographic groups—satisfying equalized odds. Different from prior works which either optimize for an equalized odds related metric during the learning process like a black-box, or manipulate the training data following some intuition; this work studies the root cause of the violation of equalized odds and how to tackle it. We found that equalizing the class distribution in each demographic group with sample weights is a necessary condition for achieving equalized odds without modifying the normal training process. In addition, an important partial condition for equalized odds (zero average odds difference) can be guaranteed when the class distributions are weighted to be not only equal but also balanced (1:1). Based on these analyses, we proposed FairBalance, a pre-processing algorithm which balances the class distribution in each demographic group by assigning calculated weights to the training data. On eight real-world datasets, our empirical results show that, at low computational overhead, the proposed pre-processing algorithm FairBalance can significantly improve equalized odds without much, if any damage to the utility. FairBalance also outperforms existing state-of-the-art approaches in terms of equalized odds. To facilitate reuse, reproduction, and validation, we made our scripts available athttps://github.com/hil-se/FairBalance.

Testing machine learning software for ethical bias has become a pressing current concern. In response, recent research has proposed a plethora of new fairness metrics, for example, the dozens of fairness metrics in the IBM AIF360 toolkit. This raises the question: How can any fairness tool satisfy such a diverse range of goals? While we cannot completely simplify the task of fairness testing, we can certainly reduce the problem. This article shows that many of those fairness metrics effectively measure the same thing. Based on experiments using seven real-world datasets, we find that (a) 26 classification metrics can be clustered into seven groups and (b) four dataset metrics can be clustered into three groups. Further, each reduced set may actually predict different things. Hence, it is no longer necessary (or even possible) to satisfy all fairness metrics. In summary, to simplify the fairness testing problem, we recommend the following steps: (1) determine what type of fairness is desirable (and we offer a handful of such types), then (2) lookup those types in our clusters, and then (3) just test for one item per cluster. For the purpose of reproducibility, our scripts and data are available at https://github.com/Repoanon ymous/Fairness_Metrics.

Context: Machine learning software can generate models that inappropriately discriminate against specific protected social groups (e.g., groups based on gender, ethnicity, etc.). Motivated by those results, software engineering researchers have proposed many methods for mitigating those discriminatory effects. While those methods are effective in mitigating bias, few of them can provide explanations on what is the root cause of bias.Objective: We aim to better detect and mitigate algorithmic discrimination in machine learning software problems.Method: Here we propose${{\sf FairMask}}$, amodel-basedextrapolation method that is capable of both mitigating bias and explaining the cause. In our${{\sf FairMask}}$approach, protected attributes are represented by models learned from the other independent variables (and these models offer extrapolations over the space between existing examples). We then use the extrapolation models to relabel protected attributes later seen in testing data or deployment time. Our approach aims to offset the biased predictions of the classification model by rebalancing the distribution of protected attributes.Results: The experiments of this paper show that, without compromising (original) model performance,${{\sf FairMask}}$can achieve significantly better group and individual fairness (as measured in different metrics) than benchmark methods. Moreover, compared to another instance-based rebalancing method, our model-based approach shows faster runtime and thus better scalability.Conclusion: Algorithmic decision bias can be removed via extrapolation that corrects the misleading latent correlation between the protected attributes and other non-protected ones. As evidence for this, our proposed${{\sf FairMask}}$is not only performance-wise better (measured by fairness and performance metrics) than two state-of-the-art fairness algorithms.Reproduction Package: In order to better support open science, all scripts and data used in this study are available online athttps://github.com/anonymous12138/biasmitigation.

Increasingly, software is making autonomous decisions in case of criminal sentencing, approving credit cards, hiring employees, and so on. Some of these decisions show bias and adversely affect certain social groups (e.g. those defined by sex, race, age, marital status). Many prior works on bias mitigation take the following form: change the data or learners in multiple ways, then see if any of that improves fairness. Perhaps a better approach is to postulate root causes of bias and then applying some resolution strategy. This paper postulates that the root causes of bias are the prior decisions that affect- (a) what data was selected and (b) the labels assigned to those examples. Our Fair-SMOTE algorithm removes biased labels; and rebalances internal distributions such that based on sensitive attribute, examples are equal in both positive and negative classes. On testing, it was seen that this method was just as effective at reducing bias as prior approaches. Further, models generated via Fair-SMOTE achieve higher performance (measured in terms of recall and F1) than other state-of-the-art fairness improvement algorithms. To the best of our knowledge, measured in terms of number of analyzed learners and datasets, this study is one of the largest studies on bias mitigation yet presented in the literature.

Machine learning software is being used in many applications (finance, hiring, admissions, criminal justice) having huge social impact. But sometimes the behavior of this software is biased and it shows discrimination based on some sensitive attributes such as sex, race etc. Prior works concentrated on finding and mitigating bias in ML models. A recent trend is using instance-based model-agnostic explanation methods such as LIME[36] to find out bias in the model prediction. Our work concentrates on finding shortcomings of current bias measures and explanation methods. We show how our proposed method based on K nearest neighbors can overcome those shortcomings and find the underlying bias of black box models. Our results are more trustworthy and helpful for the practitioners. Finally, We describe our future framework combining explanation and planning to build fair software.

Machine learning software is increasingly being used to make decisions that affect people's lives. But sometimes, the core part of this software (the learned model), behaves in a biased manner that gives undue advantages to a specific group of people (where those groups are determined by sex, race, etc.). This "algorithmic discrimination" in the AI software systems has become a matter of serious concern in the machine learning and software engineering community. There have been works done to find "algorithmic bias" or "ethical bias" in the software system. Once the bias is detected in the AI software system, the mitigation of bias is extremely important. In this work, we a)explain how ground-truth bias in training data affects machine learning model fairness and how to find that bias in AI software,b)propose a method Fairway which combines pre-processing and in-processing approach to remove ethical bias from training data and trained model. Our results show that we can find bias and mitigate bias in a learned model, without much damaging the predictive performance of that model. We propose that (1) testing for bias and (2) bias mitigation should be a routine part of the machine learning software development life cycle. Fairway offers much support for these two purposes.

Diversity, including gender diversity, is valued by many software development organizations, yet the field remains dominated by men. One reason for this lack of diversity is gender bias. In this paper, we study the effects of that bias by using an existing framework derived from the gender studies literature.We adapt the four main effects proposed in the framework by posing hypotheses about how they might manifest on GitHub,then evaluate those hypotheses quantitatively. While our results how that effects of gender bias are largely invisible on the GitHub platform itself, there are still signals of women concentrating their work in fewer places and being more restrained in communication than men.

Maintaining web-services is a mission-critical task where any down- time means loss of revenue and reputation (of being a reliable service provider). In the current competitive web services market, such a loss of reputation causes extensive loss of future revenue.