AAAI Bridge 2023
AI for Financial Institutions
Washington DC, February 8, 2023
Local time: 8:30am - 5:20pm (EST)
Central Europe time: 14:30 - 23:30 (CET)
Aim of this bridge
The aim of this AAAI bridge - organized by the Bank of Italy - is to connect two communities: the AI community and the “Financial Institution Sector” (FINST). The FINST community is populated by authorities, agencies, institutions, and other public entities that play a key role in the economic and/or financial life of their home country. A prime example are central banks, but they are by no means the end of the story: There are Financial/Banking Ombudsmans, Supervision Authorities, Financial Intelligence Units, Privacy Protection Authorities, National Statistics Institutes, and more.
These players of the public sector are in the middle of a surge of interest in AI, and can fruitfully exchange views and experiences via this bridge. They all work on economic/financial issues in which certain peculiar search / reasoning / induction / deduction / optimization / planning problems are becoming of paramount importance, with a growing fit among AI technologies, tools, techniques, and business. Usually, AI innovates FINST processes, but sometimes FINST pushes the boundaries of AI.
We expect that those who traverse the bridge from FINST to AI will discover a powerful arsenal of new and possibly unfamiliar AI techniques, described and discussed by leading experts in the field: They will likely be surprised by the reach and variety of what state-of-the-art AI has to offer, beyond the established ML approaches that have seen large adoption as of late. Those who cross the bridge the other way around will get exposed to a surprisingly rich domain, with a lot of opportunities for the application of a wide range of AI techniques on both existing and developing use-cases.
Target audience
We are open to the participation - as listeners or presenters - of any representatives from FINST entities, especially those who deal with economics/finance problems and/or have used or plan to use advanced AI tools and techniques to tackle such problems.Â
From the AI side: Any researcher, practitioners, or AI expert (or, in fact, any participant to the main AAAI conference) is welcome to join, especially those with an interest in economics & finance.
Note: This bridge aims to foster collaboration and a productive exchange of ideas and experiences among public entities with an economic role; conversely, if you work for an investment or retail bank, an insurance company, a financial intermediary, or any other private market player, you will find a suitable forum in the companion AAAI-23 bridge titled “AI for Financial Services”, to which you are encouraged to submit.
Format of the bridge
This bridge is a one-day event (February 8th, 2023) held in the context of AAAI-23. It will host 3 sessions in the course of the day. The 1st session will be a traditional keynote session with invited speakers; the 2nd and 3rd sessions are open to contributions (see “Program Schedule”).
Session 1: Invited talks
[2 hours, including Q&A - chair Marco Benedetti]
Plenary talks will be given by three renowned scientists in the field of AI who have been working in close contact with CBs and/or public economic/financial institutions. They will try to convey what it is like to work with public authorities/institutions in the “economics & finance” domain, and what are the typical AI problems (and challenges) one encounters.Session 2: Services & Software Demos
[2 hours, including Q&A - chair Alessandro Maggi]
This session will showcase 5-10 diverse, interdisciplinary projects at the intersection of AI and FINST which are already implemented or in an advanced stage of development (i.e., at least in the PoC stage, with a demo-able implementation). After a brief (15 minutes) plenary overview of all the projects, the actual interaction among attendees and proponents will be live, informal, and person-to-person. Live, hands-on demos are thus expected of all entries in Session 2.Session 3: Challenges and Use Cases
[2 hours, including Q&A - chair Oliver Giudice]
Extended abstracts or papers by FINST representatives and/or people in the AI community will be presented, in a shared, poster-like, interactive fashion. Abundant time will be allotted to Q&A.
Topics of Interest
We would be delighted to hear from the FINST community about projects, experiences, challenges, and prototypes in one or more of the following areas (non-exhaustive list, in alphabetical order):Â
AI for cybersecurity and vulnerability analysis
Blockchain analysis and intelligence
Chatbots and Virtual Agents
Data modeling and data wranglingÂ
Dealing with uncertain and/or incomplete information
Data quality issues
Data complexity of reasoning tasks
Deep fake detection, banknote authentication
Deep learning and reinforcement learning
Explainability and Ethics
Fact checking
Graph analytics
Imagery analysis for economics and finance
Intelligent Robotic Process Automation
Knowledge Representation and Reasoning
Knowledge Graphs
Localization/specialization of AI models to non-English and/or domain-specific natural languages
Multi-Agent systems simulation and calibration
Neurosymbolic reasoning
NLP and ML on hybrid (structured + unstructured) data
Pre-trained ML models and transfer learningÂ
Privacy-preserving computations
Reactive automated reasoning
Sentiment Analysis
Smart anonymization or pseudonymization of datasets
Summarization, entity recognition
Synthetic dataset and time series generation
Temporal reasoning
Topic modeling
Sample topics and issues
Just to offer a few concrete examples, consider the following three use cases.Â
Any CB is in charge of defining the monetary policy of its home country or monetary area (i.e., setting the official interest rate and controlling the money supply), and to do so there are certain non-trivial “open market” operations to execute. In particular, it must be ensured that financial entities do not submit assets as collateral which are ultimately guaranteed by issuers which are “too closely linked” with the counterparty itself. In doing these checks, one faces non-tractable search and reasoning problems under uncertain and incomplete information.
Any Supervision Authority is responsible for (macroprudential) supervision, i.e., for regulating and supervising private banks and financial institutions to guarantee the financial (and price) stability within the reference monetary area. Here, the increasing interconnectedness of the financial world makes it so that the knowledge to be exploited to establish who controls whom (and through which ownership chains and which non-financial or implied links) is nowadays to be delegated to a neurosymbolic AI (mixing inductive and deductive approaches).Â
Financial Intelligence Units are often responsible for tracing illegal financial activities related to money laundering and terrorism financing, among others. In this case, a bulk of unstructured, extremely sensitive, and oftentimes classified information has to be learned from by some complex AI; the challenge is that the human intelligence controlling the AI does not have access, for security reasons, to all of the knowledge the AI itself can see and has to reason about.
Program Schedule & Contributions
February 8, 2023
Walter E. Washington Convention Center | Room 207B
(The schedule is in EST timetable, i.e., UTC -5; for participants in Europe, i.e., UTC +1, the start time is 14:30 CET)
Â
8:30-8:45 FINst Bridge welcome
Marco Benedetti (Bank of Italy)
Session 1: Invited Talks
Chair: Marco Benedetti (Bank of Italy)
8:45-9:20 “From Strings to Things and Back: Putting AI into Action in a Central Bank”
Luigi Bellomarini (Bank of Italy)
9:20-9:55 “Reasoning with Knowledge Graphs in Finance”
Emanuel Sallinger (TU Wien, University of Oxford)
9:55-10:30 “Explainable Fact Checking for Statistical and Temporal Claims”
Paolo Papotti (EURECOM)
10:30-10:45 Coffee break
Session 2: Services & Software Demos
Chair: Alessandro Maggi (Bank of Italy)
10:45-11:05 “BLE Demo - Data-intensive AI without Data, at a FINst” 📄 PDF
Marco Benedetti, Oliver Giudice, Michela Iezzi, Alessandro Maggi (Bank of Italy)
11:05-11:25 “Augmenting Bank and Economic Data for Bank Stress-Testing with Generative Adversarial Networks” 📄 PDF
Akash Sedai, Francesca Medda, Thomas Schroeder (University College London)
11:25-11:45 “KG-Roar Demo - Interactive Reasoning on FIN-ST Knowledge Graphs” 📄 PDF
Luigi Bellomarini, Marco Benedetti, Andrea Gentili (Bank of Italy)
Emanuel Sallinger (TU Wien; University of Oxford)
11:45-12:05 “Moneying - An Artificial Intelligence platform for RegTech and AML” 📄 PDF
Salvatore Iiritano, Francesco Cupello (Revelis Srl)
Simone Mungari, Francesco Ricca (UniversitĂ della Calabria)
Ettore Ritacco (UniversitĂ di Udine)
Giuseppe Manco (ICAR-CNR)
12:05-12:25 “RIOT Demo - AI-supported Mitigation of Cyber-risk within FINst” 📄 PDF
Marco Benedetti, Andrea Gentili, Marco Mori (Bank of Italy)
12:25-12:45 “Black-it Demo - Calibrating Multi-Agent Systems to Mimic FINst Realities” 📄 PDF
Marco Benedetti, Francesco De Sclavis, Marco Favorito, Andrea Gentili, Aldo Glielmo, Davide Magnanimi, Antonio Muci (Bank of Italy)
12:45-14:10 Lunch break
Session 3: Challenges & Use Cases
Chair: Oliver Giudice (Bank of Italy)
14:10-14:30 “Combining search strategies to improve performance in the calibration of economic ABMs” 📄 PDF (arXiv)
Marco Favorito, Aldo Glielmo (Bank of Italy)
Debmallya Chanda (UniversitĂ Cattolica del Sacro Cuore, Universitat Bielefeld)
Domenico Delli Gatti (UniversitĂ Cattolica del Sacro Cuore)
14:30-14:50 “Picking out the Right Language to Automate FINST Reasoning Tasks” 📄 PDF
Teodoro Baldazzi (UniversitĂ Roma Tre)
Luigi Bellomarini (Bank of Italy)
Emanuel Sallinger (TU Wien, University of Oxford)
14:50-15:10 “NLP-based Decision Support System for Examination of Eligibility Criteria from Securities Prospectuses at the German Central Bank” 📄 PDF
Christian Hänig, Serhii Hamotskyi (Anhalt University of Applied Sciences)
Janek Blankenburg, Markus Schlösser, Gent Zambaku (Deutsche Bundesbank)
15:10-15:30 “Using ML and NLP to Understand the Trend of Adoption of Homomorphic Encryption by Financial Institutions” 📄 PDF
Danilo A. Giannone (Alan Turing Institute)
Carsten Maple (University of Warwick)
Michela Iezzi (Bank of Italy)
15:30-15:50 Coffee break
15:50-16:10 “Applied Semantics Extraction and Analytics from SEBI Documents” 📄 PDF
Pulkit Parikh, Lini Thomas, Kamalakar Karlapalem (IIIT Hyderabad)
Natraj Raman (JPMorgan AI Research)
16:10-16:30 “Automatic Information Extraction from Financial Documents for Market Supervision” 📄 PDF
Federico M. Scafoglieri, Domenico Lembo, Maurizio Lenzerini, Alessandra Monaco, Giulia Neccia (Sapienza UniversitĂ di Roma)
Alessandra Limosani (Consob)
Francesca Medda (University College London, Consob)
16:30-16:50 “NLP and ML from a FINst Perspective - Results and Challenges” 📄 PDF
Marco Benedetti, Oliver Giudice, Alessandro Maggi, Marco Mori (Bank of Italy)
16:50-17:10 “Modeling the Effect of Cascading Stop-Losses and Its Impact on Price Dynamics” 📄 PDF
Patrick Liston, Charles Gretton, Artem Lenskiy (The Australian National University)
17:10-17:20 Concluding Remarks
Important dates
November 25, 2022: Contributions to the bridge organizers due.
December 19, 2022: Notifications of acceptance.
February 8, 2023: Bridge at AAAI-23.
February 7-14, 2023: AAAI-23 Conference
Program committees & organizers
Bridge chairs
Marco Benedetti (Bank of Italy) - marco.benedetti@bancaditalia.it
Luigi Bellomarini (Bank of Italy) - luigi.bellomarini@bancaditalia.it
Bridge (local) organizer
Alessandro Maggi (Bank of Italy) - alessandro.maggi@bancaditalia.it
Bridge editorial workflow
Sara Corbo (Bank of Italy) - sara.corbo@bancaditalia.it
PC members - AcademicÂ
Alberto Finzi (University of Naples, IT)
Andrea Calì (Birkbeck University, UK)
Domenico Lembo (La Sapienza University, IT)
Danilo Antonino Giannone (Alan Turing Institute, UK)
Emanuel Sallinger (TU Wien, AT)
Fabrizio Lillo (UniversitĂ di Bologna and Scuola Normale Superiore, IT)
Fosca Giannotti (Scuola Normale Superiore, IT)
Francesca Medda (UCL, UK)
Georg Gottlob (Oxford, UK)
Giuseppe De Giacomo (Oxford, UK)
Maurizio Lenzerini (La Sapienza University, IT)
Mihai Cucuringu (Oxford and Alan Turing Institute, UK)
Piero Poccianti (Italian Association for Artificial Intelligence, IT)
Paolo Papotti (EURECOM, FR)
Sahar Vahdati (InfAI, DE)
Stefano Bistarelli (University of Perugia, IT)
PC members - InstitutionalÂ
(Affiliation is “Bank of Italy, ICT Directorate”, unless noted otherwise)Aldo GlielmoÂ
Antonino Virgillito (National Revenue Agency, IT)Â
Claudia Biancotti (Directorate General for Economics, Statistics and Research; Bank of Italy)
Davide Magnanimi
Eleonora Laurenza (Financial Intelligence Unit; Bank of Italy)
Emanuela Girardi (popAI, IT)
Erik Teunissen (De Nederlandsche Bank)
Fabiana Rossi
Juri Marcucci (Directorate General for Economics, Statistics and Research; Bank of Italy)
Luca Mossink (European Central Bank)
Livia Blasi
Nuno Pereira (Banco de Portugal)
Oliver Giudice
Pietro Franchini (IVASS, the Institute for the Supervision of Insurance, IT)
Valerio Colitta (Directorate General for Financial Supervision and Regulation; Bank of Italy)