eXplainable Artificial Intelligence (XAI): Actionable Recourse in Machine Learning Classification Models

Classification models are often used to make decisions that affect humans: whether to approve a loan application, extend a job offer, or provide insurance. In such applications, it is desirable for the individuals to not only knowing the results but also have the ability to change the decisions of the model. For example, when a person is denied a loan by a credit scoring model, in addition to know why he/she can not received the loan, it is meaningful for the person to know what he/she can do to influence the decision, i.e. what are the input variables that, if values are changed, can alter the decision of the model. Otherwise, without this information, he/she will be denied the loan as long as the model is deployed, and – more importantly – will lack agency over a decision that affects their livelihood.

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.

Emneord: XAI, Machine Learning, Optimization, actionable recourse
Publisert 25. feb. 2020 09:15 - Sist endret 26. feb. 2020 12:35

Omfang (studiepoeng)