Timezone: »
Finance is a rich domain for AI and ML research. Model-driven strategies for stock trading and risk assessment models for loan approvals are quintessential financial applications that are reasonably well-understood. However, there are a number of other applications that call for attention as well.
In particular, many finance domains involve ecosystems of interacting and competing agents. Consider for instance the detection of financial fraud and money-laundering. This is a challenging multi-agent learning problem, especially because the real world agents involved evolve their strategies constantly. Similarly, in algorithmic trading of stocks, commodities, etc., the actions of any given trading agent affects, and is affected by, other trading agents -- many of these agents are constantly learning in order to adapt to evolving market scenarios. Further, such trading agents operate at such a speed and scale that they must be fully autonomous. They have grown in sophistication to employ advanced ML strategies including deep learning, reinforcement learning, and transfer learning.
Financial institutions have a long history of investing in technology as a differentiator and have been key drivers in advancing computing infrastructure (e.g., low-latency networking). As more financial applications employ deep learning and reinforcement learning, there is consensus now on the need for more advanced computing architectures--for training large machine learning models and simulating large multi-agent learning systems--that balance scale with the stringent privacy requirements of finance.
Historically, financial firms have been highly secretive about their proprietary technology developments. But now, there is also emerging consensus on the need for (1) deeper engagement with academia to advance a shared knowledge of the unique challenges faced in FinTech, and (2) more open collaboration with academic and technology partners through intellectually sophisticated fora such as this proposed workshop.
Fri 9:00 a.m. - 9:10 a.m.
|
Opening Remarks
(
Talk
)
|
Prashant Reddy · Senthil Kumar 🔗 |
Fri 9:10 a.m. - 9:30 a.m.
|
Invited Talk 1: Adaptive Tolling for Multiagent Traffic Optimization
(
Invited Talk
)
|
Peter Stone 🔗 |
Fri 9:30 a.m. - 9:50 a.m.
|
Invited Talk 2: The Strategic Perils of Learning from Historical Data
(
Invited Talk
)
|
Jamie Morgenstern 🔗 |
Fri 9:50 a.m. - 10:30 a.m.
|
Oral Paper Presentations 1
(
Talk
)
09:50-10:03 Risk-Sensitive Compact Decision Trees for Autonomous Execution in presence of Simulated Market Response, Svitlana Vyetrenko (JP Morgan Chase); Kyle Xu (Georgia Institute of Technology) 10:04-10:16 Robust Trading via Adversarial Reinforcement Learning Thomas Spooner (University of Liverpool); Rahul Savani (Univ. of Liverpool) 10:17-10:30 Generating Realistic Stock Market Order Streams, Junyi Li (University of Michigan); Xintong Wang (University of Michigan); Yaoyang Lin (University of Michigan); Arunesh Sinha (University of Michigan); Michael Wellman (University of Michigan) |
🔗 |
Fri 10:30 a.m. - 11:00 a.m.
|
Coffee Break and Socialization
|
🔗 |
Fri 11:00 a.m. - 11:20 a.m.
|
Invited Talk 3: Trend-Following Trading Strategies and Financial Market Stability
(
Invited Talk
)
|
Michael Wellman 🔗 |
Fri 11:20 a.m. - 12:00 p.m.
|
Poster Highlights - Lightning Round
(
Talk
)
Self Organizing Supply Chains for Micro-Prediction; Present and Future Uses of the ROAR Protocol, Peter D Cotton (JP Morgan Chase) Learning-Based Trading Strategies in the Face of Market Manipulation, Xintong Wang (University of Michigan); Chris Hoang (University of Michigan); Michael Wellman (University of Michigan) Multi-Agent Simulation for Pricing and Hedging in a Dealer Market, Sumitra Ganesh (JPMorgan AI Research); Nelson Vadori (JPMorgan AI Research); Mengda Xu (JPMorgan AI Research); Hua Zheng (JPMorgan Chase); Prashant Reddy (JPMorgan AI Research); Manuela Veloso (JPMorgan AI Research) Multi-Agent Reinforcement Learning for Liquidation Strategy Analysis, Wenhang Bao (Columbia University); Xiao-Yang Liu (Columbia University) Some people aren't worth listening to: periodically retraining classifiers with feedback from a team of end users, Joshua Lockhart (JPMorgan AI Research); Mahmoud Mahfouz (JPMorgan AI Research); Tucker Balch (JPMorgan AI Research); Manuela Veloso (JPMorgan AI Research) Optimistic Bull or Pessimistic Bear: Adaptive Deep Reinforcement Learning for Stock Portfolio Allocation, Xinyi Li (Columbia University); Yinchuan Li ( Beijing Institute of Technology); Yuancheng Zhan (University of Science and Technology of China); Xiao-Yang Liu (Columbia University) How to Evaluate Trading Strategies: Backtesting or Agent-based Simulation?, Tucker Balch (JPMorgan AI Research); David Byrd (Georgia Tech); Mahmoud Mahfouz (JPMorgan AI Research) Deep Reinforcement Learning for Optimal Trade Execution, Siyu Lin (University of Virginia) |
🔗 |
Fri 12:00 p.m. - 2:00 p.m.
|
Lunch
|
🔗 |
Fri 2:00 p.m. - 2:20 p.m.
|
Invited Talk 4: Towards AI Innovation in the Financial Domain
(
Invited Talk
)
|
Manuela Veloso 🔗 |
Fri 2:20 p.m. - 3:00 p.m.
|
Oral Paper Presentations 2
(
Talk
)
02:20-02:33 Towards Inverse Reinforcement Learning for Limit Order Book Dynamics, Jacobo Roa Vicens (University College London); Cyrine Chtourou (JPMorgan Chase); Angelos Filos (University of Oxford); Francisco Rullan (University College of London); Yarin Gal (University of Oxford); Ricardo Silva (University College London) 02:34-02:47 An Agent-Based Model of Financial Benchmark Manipulation, Megan J Shearer (University of Michigan); Gabriel Rauterberg (University of Michigan); Michael Wellman (University of Michigan) 02:47-03:00 The sharp, the flat and the shallow: Can weakly interacting agents learn to escape bad minima?, Panos Parpas (Imperial College London); Nikolas Kantas (Imperial College London); Grigorios Pavliotis (Imperial College London) |
🔗 |
Fri 3:00 p.m. - 3:30 p.m.
|
Coffee Break and Socialization
|
🔗 |
Fri 3:30 p.m. - 3:50 p.m.
|
Invited Talk 5: Intra-day Stock Price Prediction as a Measure of Market Efficiency
(
Invited Talk
)
|
Tucker Balch 🔗 |
Fri 3:50 p.m. - 4:10 p.m.
|
Invited Talk 6: RLlib: A Platform for Finance Research
(
Invited Talk
)
|
Ion Stoica 🔗 |
Fri 4:10 p.m. - 5:00 p.m.
|
Poster Session - All Accepted Papers
(
Poster Session
)
|
🔗 |
Fri 6:00 p.m. - 8:00 p.m.
|
ICML Reception
(
Reception
)
|
🔗 |
Author Information
Prashant Reddy (JPMorgan AI Research)
Tucker Balch (JPMorgan AI Research)
Michael Wellman (University of Michigan)
Senthil Kumar (Capital One)
Ion Stoica (UC Berkeley)
Edith Elkind (University of Oxford)
More from the Same Authors
-
2022 Poster: POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging »
Shishir G. Patil · Paras Jain · Prabal Dutta · Ion Stoica · Joseph E Gonzalez -
2022 Spotlight: POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging »
Shishir G. Patil · Paras Jain · Prabal Dutta · Ion Stoica · Joseph E Gonzalez -
2022 : Trends Driving Big Models »
Ion Stoica -
2022 Tutorial: Welcome to the "Big Model" Era: Techniques and Systems to Train and Serve Bigger Models »
Hao Zhang · Lianmin Zheng · Zhuohan Li · Ion Stoica -
2021 Workshop: ICML Workshop on Representation Learning for Finance and E-Commerce Applications »
Senthil Kumar · Sameena Shah · Joan Bruna · Tom Goldstein · Erik Mueller · Oleg Rokhlenko · Hongxia Yang · Jianpeng Xu · Oluwatobi O Olabiyi · Charese Smiley · C. Bayan Bruss · Saurabh H Nagrecha · Svitlana Vyetrenko -
2021 Poster: ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training »
Jianfei Chen · Lianmin Zheng · Zhewei Yao · Dequan Wang · Ion Stoica · Michael Mahoney · Joseph E Gonzalez -
2021 Oral: ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training »
Jianfei Chen · Lianmin Zheng · Zhewei Yao · Dequan Wang · Ion Stoica · Michael Mahoney · Joseph E Gonzalez -
2020 Poster: Variable Skipping for Autoregressive Range Density Estimation »
Eric Liang · Zongheng Yang · Ion Stoica · Pieter Abbeel · Yan Duan · Peter Chen -
2020 Poster: FetchSGD: Communication-Efficient Federated Learning with Sketching »
Daniel Rothchild · Ashwinee Panda · Enayat Ullah · Nikita Ivkin · Ion Stoica · Vladimir Braverman · Joseph E Gonzalez · Raman Arora -
2019 : Invited Talk 6: RLlib: A Platform for Finance Research »
Ion Stoica -
2019 : Invited Talk 5: Intra-day Stock Price Prediction as a Measure of Market Efficiency »
Tucker Balch -
2019 : Invited Talk 3: Trend-Following Trading Strategies and Financial Market Stability »
Michael Wellman -
2019 : Opening Remarks »
Prashant Reddy · Senthil Kumar -
2018 Poster: RLlib: Abstractions for Distributed Reinforcement Learning »
Eric Liang · Richard Liaw · Robert Nishihara · Philipp Moritz · Roy Fox · Ken Goldberg · Joseph E Gonzalez · Michael Jordan · Ion Stoica -
2018 Oral: RLlib: Abstractions for Distributed Reinforcement Learning »
Eric Liang · Richard Liaw · Robert Nishihara · Philipp Moritz · Roy Fox · Ken Goldberg · Joseph E Gonzalez · Michael Jordan · Ion Stoica