<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
<p>CALL FOR PAPERS </p>
<div class="WordSection1">
<p class="MsoNormal">The First International Workshop on XAI in
Finance (XAI-FIN) will take place virtually on November 3, 2021,
as part of the 2021 ACM International Conference on AI in
Finance (ICAIF). For more information and updates, please visit
the workshop website at <a class="moz-txt-link-freetext"
href="https://www.doc.ic.ac.uk/~afr114/ICAIF/index.html">https://www.doc.ic.ac.uk/~afr114/ICAIF/index.html</a></p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">===Important Dates===</p>
<p class="MsoNormal">Submission deadline: 1 October 2021</p>
<p class="MsoNormal">Author notification: 15 October 2021</p>
<p class="MsoNormal">Workshop: 3 November 2021, 8am-12pm EST</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">===Overview===</p>
<p class="MsoNormal">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</p>
<p class="MsoNormal">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. </p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">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.</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">===Topics===</p>
<p class="MsoNormal">Topics include, but are not limited to, the
following:</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">-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.</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">-Practical deployment of XAI within financial
domains: best practices and lessons learned.</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">-Reviews highlighting important challenges
and open problems within XAI for Finance.</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">-User studies of consumer response to XAI
techniques and AI model outputs.</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">-Novel datasets for use within the XAI in
Finance community.</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">-Discussion on industry areas that are less
automated and how best to leverage XAI moving forward.</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">-Quantitative approaches to financial
regulation description and enforcement.</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">===Formatting===</p>
<p class="MsoNormal">We invite submissions on easychair (<a
class="moz-txt-link-freetext"
href="https://easychair.org/conferences/?conf=xaif21">https://easychair.org/conferences/?conf=xaif21</a>)
of short papers (4 pages plus up to one page for references) and
long papers (8 pages plus up to one page for references). </p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">Papers must be formatted according to ACM’s
sigconf layout. Papers must be</p>
<p class="MsoNormal">submitted in pdf format on easychair and do
not need to be anonymous. </p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">===Workshop Organizers===</p>
<p class="MsoNormal">Anupam Dutta, PhD, Professor at Electrical
and Computer Engineering Department and (by courtesy) Computer
Science Department, Carnegie Mellon University Silicon Valley </p>
<p class="MsoNormal"><a
href="http://www.andrew.cmu.edu/user/danupam/">http://www.andrew.cmu.edu/user/danupam/</a></p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">Himabindu Lakkaraju, PhD, Assistant Professor
at Harvard University with appointments in Business School and
Department of Computer Science </p>
<p class="MsoNormal"><a href="https://himalakkaraju.github.io/">https://himalakkaraju.github.io/</a></p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">Daniele Magazzeni, PhD, AI Research Director
and Head of the Explainable AI Center of Excellence, J.P. Morgan
AI Research</p>
<p class="MsoNormal"><a
href="https://www.jpmorgan.com/technology/artificial-intelligence">https://www.jpmorgan.com/technology/artificial-intelligence</a></p>
</div>
<br>
<p class="MsoNormal">Francesca Toni, PhD, Professor in Computational
Logic at the Department of</p>
<p class="MsoNormal">Computing, Imperial College London and Royal
Academy of Engineering/J.P.</p>
<p class="MsoNormal">Morgan Research Chair in Argumentation-based
Interactive Explainable AI</p>
<p class="MsoNormal"><a href="https://www.doc.ic.ac.uk/~ft/">https://www.doc.ic.ac.uk/~ft/</a>
</p>
<br>
<pre class="moz-signature" cols="72">--
Prof Francesca Toni
Department of Computing
Imperial College London
<a class="moz-txt-link-abbreviated" href="http://www.doc.ic.ac.uk/~ft/">www.doc.ic.ac.uk/~ft/</a></pre>
</body>
</html>