We welcome submissions to the 2nd International Workshop on Explainable AI in Finance to be held on 2nd November, 2022. The workshop will be in the hybrid format and is co-located with the 3rd ACM International Conference on AI in Finance (ICAIF, https://ai-finance.org/), November 2-4, 2022 (New York City and online).

Motivation

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. There are two encompassing dimensions to this: macro-financial stability and consumer protection. Financial markets transfer enormous amounts of assets on a daily basis. AI-powered automation of a substantial fraction of these transactions, especially by big players in key markets, poses a risk to financial stability if the underlying mechanisms driving market-moving decisions are not well understood. This may trigger a crisis-risking meltdown in the worst-case scenario.

At the same time, and just as important as macro-stability, is consumer protection. 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 meaningful information 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 and financial experts to discuss the key opportunities and focus areas within XAI – both in general and to face the unique challenges in the financial sector.

Areas of Interest include (but are not limited to)

1. Novel developments for existing XAI techniques, including: global methods such as intrinsically interpretable models or surrogate modelling; local methods such as counterfactual explanations, feature attribution and argumentation; information-theoretic methods; and qualitative and quantitative metrics for explanation quality.
2. Practical deployment of XAI within financial domains: best practices and lessons learned.
3. Novel research at the intersection of XAI and other desiderata of trustworthy AI/ML (e.g., fairness, robustness, and privacy).
4. Review papers highlighting important challenges and open problems within XAI for Finance.
5. User studies of consumer response to XAI techniques and AI model outputs.
6. Novel datasets for use within the XAI in Finance community.
7. Discussion on industry areas that are less automated and how best to leverage XAI moving forward.
8. Quantitative approaches to financial regulation description and enforcement.

Important Dates

1. Submission deadline: 28th August 2022, 23:59 (anywhere on earth)

2. Author notification: 12th September 2022

3. Workshop: 2nd November 2022

Submission Guidelines

We invite submissions on EasyChair of short papers (4 pages) and long papers (8 pages). There is no limit on the number of pages for references and acknowledgments.

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.

Each paper will get atleast two reviews.

The workshop will be non-archival in format, but we are intending to share the accepted papers on the workshop webpage.

Organisation

The workshop is co-located with the 3rd ACM International Conference on AI in Finance (ICAIF) in New York City and will be organised in the hybrid format.

Workshop Co-chairs

• 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
• Saumitra Mishra, PhD, Vice President/AI Research Lead at J.P. Morgan. Member of XAI Center of Excellence at J.P. Morgan
• Adrian Weller, PhD, Principal Research Fellow in Machine Learning at the University of Cambridge and Programme Director for AI at The Alan Turing Institute
• Andreas Joseph, PhD, Senior Research Economist, Advanced Analytics Division, Bank of England, and Research Fellow at the Data Analytics for Finance and Macro (DAFM) Research Centre at King’s College London
• Xia (Ben) Hu, PhD, Associate Professor in Computer Science at Rice University