Explainable AI (XAI) forms an increasingly critical component of operations undertaken within the financial industry, brought about by the growing sophistication of state-of-the-art AI models and the demand that these models be deployed in a safe and understandable manner. The financial setting brings unique challenges to XAI due to the consequential nature of decisions taken on a daily basis. As such, automation within the financial sector is tightly regulated: in the US consumer credit space, the Equal Credit Opportunity Act (ECOA), as implemented by Regulation B, demands that explanations be provided to consumers for any adverse action by a creditor; in the EU, consumers have the right to demand explanations for automated decisions under the General Data Protection Regulation (GDPR). Safe and effective usage of AI within finance is thus contingent on a strong understanding of theoretical and applied XAI. Currently, there is no industry standard consensus on which XAI techniques are appropriate to use within the different parts of the financial industry – or if indeed the current state-of- the-art is sufficient to satisfy the needs of all stakeholders.
This workshop aims to bring together academic researchers, industry practitioners, regulators and financial experts to discuss the key opportunities and focus areas within XAI to face the unique challenges in the financial sector. The workshop will include invited talks, presentations of accepted papers and panel discussions.
Topics include, but are not limited to, the following:
Novel developments for existing XAI techniques, including: global methods such as intrinsically interpretable models or surrogate modeling; local methods such as counterfactual explanations, feature attribution and argumentation; information-theoretic methods; and qualitative and quantitative metrics for explanation quality.
Practical deployment of XAI within financial domains: best practices and lessons learned.
Reviews highlighting important challenges and open problems within XAI for Finance.
User studies of consumer response to XAI techniques and AI model outputs.
Novel datasets for use within the XAI in Finance community.
Discussion on industry areas that are less automated and how best to leverage XAI moving forward.
Quantitative approaches to financial regulation description and enforcement.
We invite submissions on EasyChair of short papers (4 pages plus up to one page for references) and long papers (8 pages plus up to one page for references).
Papers must be formatted according to ACM’s sigconf layout. Papers must be submitted in pdf format on EasyChair and do not need to be anonymous.
Anupam Datta, PhD, Professor at Electrical and Computer Engineering Department and (by courtesy) Computer Science Department, Carnegie Mellon University Silicon Valley
Himabindu Lakkaraju, PhD, Assistant Professor at Harvard University with appointments in Business School and Department of Computer Science
Daniele Magazzeni, PhD, AI Research Director and Head of the Explainable AI Center of Excellence, J.P. Morgan AI Research
Francesca Toni, PhD, Professor in Computational Logic at the Department of Computing, Imperial College London and Royal Academy of Engineering / J.P. Morgan Research Chair in Argumentation-based Interactive Explainable AI
See "Accessing the Workshop" tab for instructions on how to join the Workshop.