In this project, the student will research on auditing machine learning classification model in terms of recourse, which is defined as the ability of a person to change the decision of the model through actionable input variables (e.g., income vs. gender, age, or marital status). The main work will be proposing a framework to generate a list of actionable changes for an individual to obtain the desired outcome from the classifier. The resultant framework is beneficial for practitioners, policymakers, and consumers to know what is affecting a decision of the AI-based decision system and what can they do to reverse its decision in their favour. Moreover, it provides explanations/reasons about a decision which can be used for justification. This topic is considered as one of the top research areas in XAI and the student will have the opportunity to collaborate with industry.
We expect the interested student to have a good background in machine learning and data mining algorithms as well as Python programming language. Familiarity with the evolutionary/mathematical optimization algorithms or constraint solving is an advantage.