Interpretable or Explainable-AI?
Future of Fintech
Machine learning (ML) may be the future for investment management, but most ML approaches suffer from a dangerous affliction: the black-box problem. You may be able to observe the inputs to an ML approach, but how the outputs are reached can be a mystery. If as an investment manager you cannot explain your investment decisions to Compliance executives, regulators or clients, you might be exposing your firm to unacceptable levels of legal and regulatory risk*.
Our webinar brings together world authorities on the two solutions currently posed for the black-box problem: interpretable AI, where black-box approaches are rejected in favour of more simple, interpretable models; or explainable AI (XAI), where we attempt to explain the inner workings of black-box approaches.
* see comments from CFA Institute, 2019,; FINRA, 2020
Presenters
Spotlights
Explainable, Interpretable AI: The Future of Investment Management Schedule
Schedule: 2pm - 4pm London Time (9am - 11am EST)
Friday 19th November 2021
14:00
Dr Dan Philps and Professor Ram Gopal introduce one of the hottest topics in finance
Open
Interpret or Explain?
Interpretable AI
Explainable AI
Hybrid systems
Sprint Panel
14:10
Professor Cynthia Rudin, Duke University
14:30
Dr Daniele Magazzeni, JP Morgan XAI center of excellence
14:50
Professor Artur d'Avila Garcez, City, University of London
15:10
Fast format panel discussion
Research Spotlights
15:25
Applied Interpretable AI
Dr Timothy Law, Rothko Investment Strategies
XAI
15:35
Dr Adriano Koshiyama, UCL
Graph nets
15:45
Dr Pasquale Minervini, UCL
Close
15:55
Closing remarks from Dr Dan Philps and Prof Ram Gopal
Presenters' Organisations

Duke University
The Department of Computer Science at Duke University is an internationally recognized leader in research and education. Researchers at Duke use the tools of artificial intelligence to assist with various important societal problems, including (but not limited to) healthcare, antibiotic and cancer resistance, criminal justice, detecting fake news, allocation of public resources to those who need them, environmental sustainability, energy reliability, and political districting. For many of these applications, it is essential that the system satisfy certain interpretability, transparency, morality and/or fairness conditions.

J.P. Morgan
In July 2020, J.P. Morgan created the firmwide Explainable AI Center of Excellence (XAI COE), led by AI Research, to perform cutting-edge research in explainability and fairness. The XAI COE brings together researchers and practitioners to develop and share techniques, tools, and frameworks to support AI/ML model explainability and fairness, and to advance the state-of-the-art by publishing in top AI/ML venues.

City, University of London
City has been at the leading edge of computer science in the UK for six decades; from laying the groundwork for the foundation of the British Computer Society and awarding some of the country’s first Computer Science degrees, to the vibrant, modern department that exists today.

University College London
UCL Computer Science is home to some of the world's most influential and creative researchers in the field of computer science.

Rothko Investment Strategies
Rothko is a systematic investment manager, driven by interpretable Artificial Intelligence (A.I.), specializing in international and emerging equity strategies. We believe alpha can be systematically extracted from inefficient asset classes and that A.I. can be used to learn and shape a systematic approach.

Hosting and Moderating

Professor Ram Gopal
Professor of Information Systems and Management at the Warwick Business School

Dr Dan Philps
Head of Rothko Investment Strategies, Honorary Research Fellow of University of Warwick

