Please update your browser.
Artificial Intelligence Research
J.P. Morgan AI Research Publications
(all authors are from J.P. Morgan AI Research, unless otherwise noted)
Journals
Synthetic Document Generator for Annotation-free Layout Recognition
Natraj Raman, Sameena Shah, Manuela Veloso
Pattern Recognition Journal Vol 128, August 2022
Conferences
Improving compositional generalization for multi-step quantitative reasoning in question answering
Armineh Nourbakhsh, Cathy Jiao, Sameena Shah, Carolyn Rose
Experimental Methods in Natural Language Processing (EMNLP), December 2022
Intent classification using pre-trained embeddings for low resource languages
Hemant Yadav, Akshat Gupta, Sai Krishna Rallabandi, Alan W Black, Rajiv Ratn Shah
Interspeech 2022, September 2022
Prio+: Privacy Preserving Aggregate Statistics via Boolean Shares
Surya Addanki, Kevin Garbe, Eli Jaffe, Rafail Ostrovsky, Antigoni Polychroniadou
SCN 2022, September 2022
Structure and Semantics Preserving Document Representations
Natraj Raman, Sameena Shah and Manuela Veloso
SIGIR 2022, July 2022
Explaining Preference-driven Schedules: the EXPRES Framework (Extended Version)
Alberto Pozanco, Francesca Mosca, Parisa Zehtabi, Daniele Magazzeni, Sarit Kraus
ICAPS 2022, July 2022
Consensus Multiplicative Weights Update: Learning to Learn using Projector-based Game Signatures
Nelson Vadori, Rahul Savani, Thomas Spooner, Sumitra Ganesh
ICML, July 2022
Click here for video presentation
Sharing Transformation and Dishonest Majority MPC with Packed Secret Sharing
Vipul Goyal, Antigoni Polychroniadou, Yifan Song
CRYPTO 2022, July 2022
Fast Fully Secure Multi-Party Computation over Any Ring with Two-Thirds Honest Majority
Anders Dalskov, Daniel Escudero, and Ariel Nof
ACM Conference on Computer and Communications Security (CCS), July 2022
More Efficient Dishonest Majority Secure Computation over Z_2^k via Galois Rings
Daniel Escudero, Chaoping Xing, Chen Yuan
CRYPTO 2022, July 2022
Assignment and Prioritization of Tasks with Uncertain Durations for Satisfying Makespans in Decentralized Execution
Sriram Gopalakrishnan, Daniel Borrajo
ICAPS 2022, June 2022
Explaining Preference-driven Schedules: the EXPRES Framework
Alberto Pozanco, Francesca Mosca, Parisa Zehtabi, Daniele Magazzeni, Sarit Kraus
ICAPS 2022, June 2022
Counterfactual Shapley Additive Explanations
Emanuele Albini, Jason Long, Danial Dervovic, Daniele Magazzeni
2022 ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT 2022), June 2022
Kicking-the-Bucket: Fast Privacy-Preserving Trading Using Buckets
Mariana Botelho da Gama, John Cartlidge, Antigoni Polychroniadou, Nigel P. Smart, Younes Talibi Alaoui
Financial Cryptography 2022, May 2022
Lightweight, Maliciously Secure Verifiable Function Secret Sharing
Leo de Castro, Antigoni Polychroniadou
EUROCRYPT 2022, May 2022
Advising Agent for Service-Providing Live-Chat Operators. [Extended Abstract]
Aviram Aviv, Yaniv Oshrat, Samuel A. Assefa, Tobi Mustapha, Daniel Borrajo, Manuela Veloso, Sarit Kraus
AAMAS 2022, May 2022
Counterfactual Shapley Additive Explanations
Emanuele Albini, Jason Long, Danial Dervovic, Daniele Magazzeni
FAccT, January 2022
Workshops
PFPT: a Personal Finance Planning Tool by means of Heuristic Search and Automated Planning
Alberto Pozanco, Kassiani Papasotiriou, Daniel Borrajo
FinPlan workshop in ICAPS 2022, July 2022
On Building Spoken Language Understanding Systems for Low Resourced Languages
Akshat Gupta
SIGMORPHON, co-located with NAACL 2022, July 2022
Buggana Sathvik, Shivam Mangale, Deepti Saravanan, Shravya Kanchi, Ujwal Narayan, Lini Thomas, Kamalakar Karlapalem and Natraj Raman
FinWeb Workshop in TheWebConf 2023, May 2022
Detecting Regulation Violations for an Indian Regulatory body through multilabel classification
Ujwal Narayan, Pulkit Parikh, Kamalakar Karlapalem, and Natraj Raman
FinWeb Workshop in TheWebConf 2022, May 2022
AI for Code Updates
Salwa Alamir, Petr Babkin, Nacho Navarro, and Sameena Shah
44th International Conference on Software Engineering: Software Engineering in Practice, May 2022
Global Counterfactual Explanations: Investigations, Implementations and Improvements
Dan Ley & Saumitra Mishra ICR WS, March 2022
CTMSTOU Driven Markets: simulated environment for regime-awareness in trading policies
Selim Amrouni, Aymeric Moulin, Tucker Balch
AAAI’22, February 2022
Towards learning to explain with concept bottleneck models: mitigating information leakage
Joshua Lockhart
ICLR Workshop on Socially Responsible Machine Learning, January 2022
Journals
Journal of Cryptology 2021Round-Optimal Secure Multi-party Computation.
Shai Halevi, Carmit Hazay, Antigoni Polychroniadou, Muthuramakrishnan Venkitasubramaniam
Journal of Cryptology 2021
Artificial intelligence research in finance: discussion and examples
Manuela Veloso, Tucker Balch, Daniel Borrajo, Prashant Reddy, Sameena Shah
Oxford Review of Economic Policy, Volume 37, Issue 3, Autumn 2021, Pages 564–584
Conferences
Factored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPs
Thomas Spooner, Nelson Vadori, Sumitra Ganesh
In General Proceedings of NeurIPS’21, December 2021
Improved Single-Round Secure Multiplication Using Regenerating Codes.
Mark Abspoel, Ronald Cramer, Daniel Escudero, Ivan Damgård and Chaoping Xing
ASIACRYPT’21, December 2021
Visual Forecasting of Time Series with Image-to-Image Regression
Naftali Cohen, Srijan Sood, Zhen Zeng, Tucker Balch, Manuela Veloso
ICAF 2021, November 2021
Learning to Classify and Imitate Trading Agents in Continuous Double Market Auction
Mahmoud Mahfouz, Tucker Balch, Manuela Veloso, Danilo Mandic
In General Proceedings of ICAIF ’21, November 2021
Selim Amrouni, Aymeric Moulin, Jared Vann, Svitlana Vyetrenko, Tucker Balch, Manuela Veloso
In General Proceedings of ICAIF ’21, November 2021
Profit equitably: An investigation of market maker’s impact on equitable outcomes
Kshama Dwarakanath, Svitlana Vyetrenko, Tucker Balch
In General Proceedings of ICAIF ’21, November 2021
Deep Video Prediction for Time Series Forecasting
Zhen Zeng, Tucker Balch, Manuela Veloso
ICAIF’21, November 2021
Information-Theoretically Secure MPC against Mixed Dynamic Adversaries.
Ivan Damgård, Daniel Escudero and Divya Ravi
TCC’21, November 2021
Intelligent Execution through Plan Analysis
Daniel Borrajo, Manuela Veloso
In General Proceedings of
IROS'21, October 2021
Computing Opportunities to Augment Plans for Novel Replanning during Execution
Daniel Borrajo, Manuela Veloso
In General Proceedings of ICAPS’21, August 2021
Towards a fully RL-based Market Simulator
Leo Ardon, Nelson Vadori, Thomas Spooner, Mengda Xu, Jared Vann, Sumitra Ganesh
ACM International Conference on AI in Finance, October 2021
Non-parametric stochastic sequential assignment with random arrival times
Danial Dervovic, Parisa Hassanzadeh, Samuel Assefa, Prashant Reddy
In General Proceedings of IJCAI'21, August 2021
Unconditional Communication-Efficient MPC via Hall's Marriage Theorem
Vipul Goyal, Antigoni Polychroniadou, Yifan Song
CRYPTO 2021 - 41st Annual International Cryptology Conference, June 2021
ATLAS: Efficient and Scalable MPC in the Honest Majority Setting
Vipul Goyal, Hanjun Li, Rafail Ostrovsky, Antigoni Polychroniadou, Yifan Song
CRYPTO 2021 - 41st Annual International Cryptology Conference, June 2021
FinQA: A Data Set of Numerical Reasoning over Financial Data
Zhinyu Zhen, Wenhu Chen, Charese Smiley, Sameena Shah, Iana Borova, Dylan Langdom, Reema Mousa, Matt Beane, Ting-Hao Huang, Bryan Routledge, William Yang Wang
In General Proceedings of EMNLP’21, April 2021
Constant-Overhead Unconditionally Secure Multiparty Computation over Binary Fields
Antigoni Polychroniadou, Yifan Song
EUROCRYPT 2021 - 40th Annual International Conference on the Theory and Applications of Cryptographic Techniques, March 2021
Workshops
Mixture of Basis for Interpretable Continual Learning with Distribution Shifts
Mengda Xu, Sumitra Ganesh, Pranay Pasula
NeurIPS 2021 Distribution Shifts (DistShift) Workshop, December 2021
Fair when trained, unfair when deployed: fairness in performative prediction settings
Alan Mishler, Niccolo Dalmasso
NeurIPS 2021 Workshop on Algorithmic Fairness through Causality and Robustness, December 2021
Efficient Calibration of Multi-Agent Market Simulators from Time Series with Bayesian Optimization
Yuanlu Bai, Svitlana Vyetrenko, Henry Lam, Tucker Balch
NeurIPS 2021 Workshop on Optimization, December 2021
Parameterized Explanations for Investor/Company Matching
Simerjot Kaur, Ivan Brugere, Andrea Stefanucci, Armineh Nourbakhsh, Sameena Shah, Manuela Veloso
ICAIF’21 Explainable AI in Finance, November 2021
ACCO: Algebraic Computation with Comparison.
Xiaoqi Duan, Vipul Goyal, Hanjun Li, Rafail Ostrovsky, Antigoni Polychroniadou and Yifan Song
CCSW’21 (Cloud Computing Security Workshop), November 2021
Counterfactual Shapely Additive Values
Emanuele Albini, Jason Long, Danial Dervovic, Daniele Magazzeni
ICAIF’21 Workshop on Explainable AI in Finance, November 2021
A Survey on the Robustness of Feature Importance and Counterfactual Explanations
Saumitra Mishra, Sanghamitra Dutta, Jason Long, and Daniele Magazzeni
ICAIF’21 Workshop on Explainable AI in Finance, November 2021
A Planning Approach to Agile Project Management. The JIRA Planner
Salwa Alamir, Parisa Zehtabi, Rui Silva, Alberto Pozanco, Daniele Magazzeni, Daniel Borrajo, Sameena Shah, Manuela Veloso
ICAPS'21 Workshop on Planning for Financial Services, August 2021
Proving Security of Cryptographic Protocols using Automated Planning
Alberto Pozanco, Antigoni Polychroniadou, Daniele Magazzeni, Daniel Borrajo
ICAPS'21 Workshop on Planning for Financial Services, August 2021
Similarity Metrics for Transfer Learning in Financial Markets
Diego Pino González (Universidad Carlos III de Madrid) , Fernando Fernández Rebollo (Madrid), Francisco Javier García Polo (Madrid), Svitlana Vyetrenko
ICAPS'21 Workshop on Planning for Financial Services, August 2021
Tradeoffs in Sequential Binary Classification under Limited Inspection Resources
Parisa Hassanzadeh, Danial Dervovic, Samuel Assefa, Prashant Reddy, Manuela Veloso
KDD'21 Workshop on Machine Learning in Finance, August 2021
Visual Time Series Forecasting: An Image-driven Approach
Naftali Cohen, Srijan Sood, Zhen Zeng, Tucker Balch, Manuela Veloso
KDD'21, Workshop on Mining and Learning from Time Series, August 2021
Counterfactual Explanations for Arbitrary Regression Models
Thomas Spooner, Danial Dervovic, Jason Long, Jon Shepard, Jiahao Chen, Daniele Magazzeni
ICML’21 Workshop on Algorithmic Recourse, July 2021
Belief and Persuasion in Scientific Discourse on Social Media: A Study of the Covid-19 Pandemic
Salwa Alamir, Armineh Nourbakhsh, Cecilia Tilli, Sameena Shah, Manuela Veloso
AAAI’21 Workshop on AI for Behavior Change, February 2021
PayVAE: A Generative Model for Financial Transactions
Niccolo, Dalmaso, Robert Tillman, Prashant Reddy, Manuela Veloso
AAAI'21 Workshop on Knowledge Discovery from Unstructured Data in Financial Services, February 2021
DocuBot : Generating financial reports using natural language interactions
Vineeth Ravi, Sélim Amrouni, Andrea Stefanucci, Armineh Nourbakhsh, Prashant Reddy, Manuela Veloso
AAAI'21 Workshop on Content Authoring and Design, January 2021
Journals
Mapping ESG Trends by Distant Supervision of Neural Language Models
Natraj Raman, Grace Bang (Bloomberg LP) and Armineh Nourbakhsh
Machine Learning and Knowledge Extraction, 2020 Dec, 2(4), pp 453-468.
Conferences
Small Memory Robust Simulation of Client-Server Interactive Protocols over Oblivious Noisy Channels
T.-H. Hubert Chan (Hong Kong University), Zhibin Liang (Hong Kong University), Antigoni Polychroniadou, Elaine Shi (Cornell University)
SODA’20, 30th ACM-SIAM Symposium on Discrete Algorithms, Salt Lake City, Utah, January 2020
Succinct Non-Interactive Secure Computation
Andrew Morgan (Cornell University), Rafael Pass (Cornell University), Antigoni Polychroniadou
EUROCRYPT’20, International Conference on the Theory and Applications of Cryptographic Techniques, May 2020
Gilad Asharov, Tucker Balch, Antigoni Polychroniadou, Manuela Veloso
AAMAS’20, International Conference on Autonomous Agents and Multi-Agent Systems, Auckland, New Zealand, May 2020
Heuristics for Link Prediction in Multiplex Networks
Robert E. Tillman, Vamsi Potluru, Jiahao Chen, Prashant Reddy, Manuela Veloso
In Proceedings of ECAI'20, European Conference on Artificial Intelligence, Santiago de Compostela, Spain, June 2020
ABIDES: Towards high-fidelity multi-agent market simulation
David Byrd (Georgia Institute of Technology); Maria Hybinette (University of Georgia); Tucker Balch
2020 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation, June 2020
DeePlex: A GNN for Link Prediction in Multiplex Networks
Vamsi K. Potluru, Robert E. Tillman, Prashant Reddy, Manuela Veloso
SIAM - Network Science, July 2020
FACT: A Diagnostic for Group Fairness Trade-offs
Joon Sik Kim (CMU and JPMorgan Chase), Jiahao Chen, Ameet Talwalkar (CMU)
ICML 2020 (Virtual), August 2020
Daniel Borrajo, Manuela Veloso, Sameena Shah
International Conference on AI in Finance, October 2020
SURF: Improving Classifiers in Production by Learning From Busy and Noisy End Users
Joshua Lockhart, Samuel Assefa, Ayham Alajdad (J.P. Morgan Applied AI & ML), Andrew Alexander (J.P. Morgan Applied AI & ML), Tucker Balch, Manuela Veloso
ICAIF'20, International Conference on AI in Finance, October 2020
Get Real: Realism Metrics for Robust Limit Order Book Market Simulations
Svitlana Vyetrenko, David Byrd (Georgia Institute of Technology), Danial Dervovic, Tucker Balch, Mahmoud Mahfouz, Nicholas Petosa (Georgia Institute of Technology)
ICAIF’20, International Conference on AI in Finance, October 2020
Risk-Sensitive Reinforcement Learning: a Martingale Approach to Reward Uncertainty
Nelson Vadori, Sumitra Ganesh, Prashant Reddy, Manuela Veloso
ICAIF’20, International Conference on AI in Finance, October 2020
Trading via Image Classification
Naftali Cohen, Tucker Balch, Manuela Veloso
ICAIF’20, International Conference on AI in Finance, October 2020
SecretMatch: Inventory Matching from Fully Homomorphic Encryption
Ben Diamond, Antigoni Polychroniadou, Tucker Balch
ICAIF Conference, New York, October 2020
CryptoCredit: Securely Training Fair Models
Leo de Castro (MIT)*, Jiahao Chen, Antigoni Polychroniadou
ICAIF Conference, New York, October 2020
Eren Kursun (Columbia University), Hongda Shen (University of Alabama in Huntsville)*; Jiahao Chen
ICAIF Conference, New York, October 2020
David Byrd (Ga Tech)* & Antigoni Polychroniadou
ICAIF Conference, New York, October 2020
Generating synthetic data in finance: opportunities, challenges and pitfalls
Samuel Assefa, Danial Dervovic, Mahmoud Mahfouz , Robert Tillman , Prashant Reddy , Manuela Veloso
ICAIF Conference, New York, October 2020
Recommending Missing and Suspicious Links in Multiplex Financial Networks
Robert E Tillman, Prashant Reddy, Manuela Veloso
ICAIF Conference, New York, October 2020
Paying down metadata debt: learning the representation of concepts using topic models
Jiahao Chen & Manuela Veloso
ICAIF Conference, New York, October 2020
What can be learned from satisfaction assessments?
Naftali Cohen, Prashant Reddy, Simran Lamba
ICAIF Conference, New York, October 2020
Calibration of Shared Equilibria in General Sum Partially Observable Markov Games
Nelson Vadori, Sumitra Ganesh, Prashant Reddy, Manuela Veloso
In proceedings of NeurIPS’20, Conference on Neural Information Processing Systems, December 2020
Click here for video presentation
Workshops
Classifying and Understanding Financial Data Using Graph Neural Network
Xiaoxiao Li (Yale University), Joao Saude, Prashant Reddy, Manuela Veloso
AAAI’20 Workshop on Knowledge Discovery from Unstructured Data in Financial Services, February 2020
Similarity metrics for transfer learning in financial markets
Daniel Pino, Javier Garcia, Fernando Fernandez, Svitlana Vyetrenko
FinPlan Workshop at ICAIF, October 2020
Goal recognition via model-based and model-free techniques
Daniel Borrajo, Sriram Gopalakrishnan (Arizona State University), Vamsi K. Potluru
ICAPS’20 Workshop in Planning for Financial Services (FinPlan), November 2020
Domain-independent generation and classification of behavior traces
Daniel Borrajo, Manuela Veloso
ICAPS’20 Workshop in Planning for Financial Services (FinPlan), November 2020
Provable Multi-Objective Reinforcement Learning with Generative Models
Dongruo Zhou (USC), Jiahao Chen, Quanquan Gu (USC)
NeurIPS Workshop on Challenges of Real-World Reinforcement Learning, December 2020
Journals
Fund asset interference using machine learning methods: what’s in that portfolio?
David Byrd (Georgia Institute of Technology), Tucker Balch
Journal of Financial Data Science, July 2019
@inproceedings{Byrd2019FundAI,
title={Fund Asset Inference Using Machine Learning Methods: What’s in That Portfolio?},
author={David Byrd and Sourabh Bajaj and Tucker Hybinette Balch},
booktitle={The Journal of Financial Data Science},
year={2019}
}
Given only the historic net asset value of a large-cap mutual fund, which members of some universe of stocks are held by the fund? Discovering an exact solution is combinatorially intractable because there are, for example, C(500,30) or 1.4 × 1048 possible portfolios of 30 stocks drawn from the S&P 500. The authors extend an existing linear clones approach and introduce a new sequential oscillating selection method to produce a computationally efficient inference. Such techniques could inform efforts to detect fund window dressing of disclosure statements or to adjust market positions in advance of major fund disclosure dates. The authors test the approach by tasking the algorithm with inferring the constituents of exchange traded funds for which the components can be later examined. Depending on the details of the specific problem, the algorithm runs on consumer hardware in 8 to 15 seconds and identifies target portfolio constituents with an accuracy of 88.2% to 98.6%.
The Effect of Visual Design in Image Classification
Naftali Cohen, Tucker Balch, Manuela Veloso
August 2019
@misc{https://doi.org/10.48550/arxiv.1907.09567,
doi = {10.48550/ARXIV.1907.09567},
url = {https://arxiv.org/abs/1907.09567},
author = {Cohen, Naftali and Balch, Tucker and Veloso, Manuela},
keywords = {Computer Vision and Pattern Recognition (cs.CV), Human-Computer Interaction (cs.HC), Computational Finance (q-fin.CP), Trading and Market Microstructure (q-fin.TR), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Economics and business, FOS: Economics and business},
title = {The Effect of Visual Design in Image Classification},
publisher = {arXiv},
year = {2019},
copyright = {arXiv.org perpetual, non-exclusive license}
Financial companies continuously analyze the state of the markets to rethink and adjust their investment strategies (e.g., [8, 4, 15]). While the analysis is done on the digital form of data, decisions are often made based on graphical representations in white papers or presentation slides. In this study, we examine whether binary decisions are better to be decided based on the numeric or the visual representation of the same data. Using two data sets, a matrix of numerical data with spatial dependencies and financial data describing the state of the S&P index, we compare the results of supervised classification based on the original numerical representation and the visual transformation of the same data. We show that, for these data sets, the visual transformation results in higher predictability skill compared to the original form of the data. We suggest thinking of the visual representation of numeric data, effectively, as a combination of dimensional reduction and feature engineering techniques (e.g., [5]). In particular, if the visual layout encapsulates the full complexity of the data. In this view, thoughtful visual design can guard against overfitting, or introduce new features – all of which benefit the learning process, and effectively lead to better recognition of meaningful patterns
Conferences
Small Memory Robust Simulation of Interactive Protocols over Oblivious Noisy Channels
Hubert Chan, Zhibin Liang (Hong Kong University), Antigoni Polychroniadou, Elaine Shi (Cornell University)
ACM - SIAM'19 Symposium on Discrete Algorithms, San Diego, CA, January 2019
@misc{https://doi.org/10.48550/arxiv.1910.12175,
doi = {10.48550/ARXIV.1910.12175},
url = {https://arxiv.org/abs/1910.12175},
author = {Chan, T-H. Hubert and Liang, Zhibin and Polychroniadou, Antigoni and Shi, Elaine},
keywords = {Information Theory (cs.IT), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Small Memory Robust Simulation of Client-Server Interactive Protocols over Oblivious Noisy Channels},
publisher = {arXiv},
year = {2019},
copyright = {arXiv.org perpetual, non-exclusive license}
}
We revisit the problem of low-memory robust simulation of interactive protocols over noisy channels. Haeupler [FOCS 2014] considered robust simulation of two-party interactive protocols over oblivious, as well as adaptive, noisy channels. Since the simulation does not need to have fixed communication pattern, the achieved communication rates can circumvent the lower bound proved by Kol and Raz [STOC 2013]. However, a drawback of this approach is that each party needs to remember the whole history of the simulated transcript. In a subsequent manuscript, Haeupler and Resch considered low-memory simulation. The idea was to view the original protocol as a computational DAG and only the identities of the nodes are saved (as opposed to the whole transcript history) for backtracking to reduce memory usage. In this paper, we consider low-memory robust simulation of more general client-server interactive protocols, in which a leader communicates with other members/servers, who do not communicate among themselves; this setting can be applied to information-theoretic multi-server Private Information Retrieval (PIR) schemes. We propose an information-theoretic technique that converts any correct PIR protocol that assumes reliable channels, into a protocol which is both correct and private in the presence of a noisy channel while keeping the space complexity to a minimum. Despite the huge attention that PIR protocols have received in the literature, the existing works assume that the parties communicate using noiseless channels. Moreover, we observe that the approach of Haeupler and Resch to just save the nodes in the aforementioned DAG without taking the transcript history into account will lead to a correctness issue even for oblivious corruptions. We resolve this issue by saving hashes of prefixes of past transcripts. Departing from the DAG representation also allows us to accommodate scenarios where a party can simulate its part of the protocol without any extra knowledge (such as the DAG representation of the whole protocol). In the the two-party setting, our simulation has the same dependence on the error rate as in the work of Haeupler, and in the client-server setting it also depends on the number of servers. Furthermore, since our approach does not remember the complete transcript history, our current technique can defend only against oblivious corruptions.
Workshops
Svitlana Vyetrenko, Shaojie Xu (Georgia Institute of Technology)
ICML'19 Workshop on AI in Finance, Long Beach, CA, June 2019
@misc{https://doi.org/10.48550/arxiv.1906.02312,
doi = {10.48550/ARXIV.1906.02312},
url = {https://arxiv.org/abs/1906.02312},
author = {Vyetrenko, Svitlana and Xu, Shaojie},
keywords = {Trading and Market Microstructure (q-fin.TR), Machine Learning (cs.LG), FOS: Economics and business, FOS: Economics and business, FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Risk-Sensitive Compact Decision Trees for Autonomous Execution in Presence of Simulated Market Response},
publisher = {arXiv},
year = {2019},
copyright = {arXiv.org perpetual, non-exclusive license}
}
We demonstrate an application of risk-sensitive reinforcement learning to optimizing execution in limit order book markets. We represent taking order execution decisions based on limit order book knowledge by a Markov Decision Process; and train a trading agent in a market simulator, which emulates multi-agent interaction by synthesizing market response to our agent’s execution decisions from historical data. Due to market impact, executing high volume orders can incur significant cost. We learn trading signals from market microstructure in presence of simulated market response and derive explainable decision-tree-based execution policies using risk-sensitive Q-learning to minimize execution cost subject to constraints on cost variance.
Tucker Balch, Mahmoud Mahfouz, Joshua Lockhart, Maria Hybinette (University of Georgia), David Byrd (Georgia Institute of Technology)
ICML'19 Workshop on AI in Finance, Long Beach, CA, June 2019
@article{https://doi.org/10.48550/arxiv.1906.12010,
doi = {10.48550/ARXIV.1906.12010},
url = {https://arxiv.org/abs/1906.12010},
author = {Balch, Tucker Hybinette and Mahfouz, Mahmoud and Lockhart, Joshua and Hybinette, Maria and Byrd, David},
keywords = {Trading and Market Microstructure (q-fin.TR), Computer Science and Game Theory (cs.GT), FOS: Economics and business, FOS: Economics and business, FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {How to Evaluate Trading Strategies: Single Agent Market Replay or Multiple Agent Interactive Simulation?},
publisher = {arXiv},
year = {2019}
copyright = {arXiv.org perpetual, non-exclusive license}
}
We show how a multi-agent simulator can support two important but distinct methods for assessing a trading strategy: Market Replay and Interactive Agent-Based Simulation (IABS). Our solution is important because each method offers strengths and weaknesses that expose or conceal flaws in the subject strategy. A key weakness of Market Replay is that the simulated market does not substantially adapt to or respond to the presence of the experimental strategy. IABS methods provide an artificial market for the experimental strategy using a population of background trading agents. Because the background agents attend to market conditions and current price as part of their strategy, the overall market is responsive to the presence of the experimental strategy. Even so, IABS methods have their own weaknesses, primarily that it is unclear if the market environment they provide is realistic. We describe our approach in detail, and illustrate its use in an example application: The evaluation of market impact for various size orders.
Joshua Lockhart, Samuel Assefa, Tucker Balch, Manuela Veloso
ICML'19 Workshop on AI in Finance, Long Beach, CA, June 2019
@misc{https://doi.org/10.48550/arxiv.2004.13152,
doi = {10.48550/ARXIV.2004.13152},
url = {https://arxiv.org/abs/2004.13152},
author = {Lockhart, Joshua and Assefa, Samuel and Balch, Tucker and Veloso, Manuela},
keywords = {Machine Learning (cs.LG), Machine Learning (stat.ML), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Some people aren't worth listening to: periodically retraining classifiers with feedback from a team of end users},
publisher = {arXiv},
year = {2020},
copyright = {arXiv.org perpetual, non-exclusive license}
}
Document classification is ubiquitous in a business setting, but often the end users of a classifier are engaged in an ongoing feedback-retrain loop with the team that maintain it. We consider this feedback-retrain loop from a multi-agent point of view, considering the end users as autonomous agents that provide feedback on the labelled data provided by the classifier. This allows us to examine the effect on the classifier’s performance of unreliable end users who provide incorrect feedback. We demonstrate a classifier that can learn which users tend to be unreliable, filtering their feedback out of the loop, thus improving performance in subsequent iterations.
Multi-Agent Simulation for Pricing and Hedging in a Dealer Market
Sumitra Ganesh, Nelson Vadori*, Mengda Xu*, Hua Zheng, Prashant Reddy, Manuela Veloso
ICML'19 Workshop on AI in Finance, Long Beach, CA, June 2019
@misc{https://doi.org/10.48550/arxiv.1911.05892,
doi = {10.48550/ARXIV.1911.05892},
url = {https://arxiv.org/abs/1911.05892},
author = {Ganesh, Sumitra and Vadori, Nelson and Xu, Mengda and Zheng, Hua and Reddy, Prashant and Veloso, Manuela},
keywords = {Trading and Market Microstructure (q-fin.TR), Machine Learning (cs.LG), Multiagent Systems (cs.MA), FOS: Economics and business, FOS: Economics and business, FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Reinforcement Learning for Market Making in a Multi-agent Dealer Market},
publisher = {arXiv},
year = {2019},
copyright = {arXiv.org perpetual, non-exclusive license}
}
Financial markets contain a rich set of multiagent learning problems but lack simulators that could be used to research, develop and test reinforcement learning algorithms. In this paper, we demonstrate the use of agent based modeling to simulate a dealer market with two types of agents - market makers and investors. In particular, we focus on the dynamics that arise from price differentiation and risk management. We show through experiments that our simulation model is able to produce known effects in these markets such as varied price sensitivity among investors and the benefits of internalization for market makers.
Latent Bayesian Inference for Robust Earnings Estimates
Chirag Nagpal (Carnegie Mellon University), Robert E Tillman, Prashant Reddy, Manuela Veloso
NeurIPS'19 Workshop on Robust AI in Financial Services, Vancouver, Canada, December 2019
@article{https://doi.org/10.48550/arxiv.2004.06565,
doi = {10.48550/ARXIV.2004.06565},
url = {https://arxiv.org/abs/2004.06565},
author = {Nagpal, Chirag and Tillman, Robert E. and Reddy, Prashant and Veloso, Manuela},
keywords = {Statistical Finance (q-fin.ST), Machine Learning (cs.LG), Applications (stat.AP), Machine Learning (stat.ML), FOS: Economics and business, FOS: Economics and business, FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Bayesian Consensus: Consensus Estimates from Miscalibrated Instruments under Heteroscedastic Noise},
publisher = {arXiv}
year = {2020},
copyright = {arXiv.org perpetual, non-exclusive license}
}
We consider the problem of aggregating predictions or measurements from a set of human forecasters, models, sensors or other instruments which may be subject to bias or miscalibration and random heteroscedastic noise. We propose a Bayesian consensus estimator that adjusts for miscalibration and noise and show that this estimator is unbiased and asymptotically more efficient than naive alternatives. We further propose a Hierarchical Bayesian Model that leverages our proposed estimator and apply it to two real world forecasting challenges that require consensus estimates from error prone individual estimates: forecasting influenza like illness (ILI) weekly percentages and forecasting annual earnings of public companies. We demonstrate that our approach is effective at mitigating bias and error and results in more accurate forecasts than existing consensus models.
On the Importance of Opponent Modeling in Auction Markets
Mahmoud Mahfouz, Angelos Filos, Cyrine Chtourou, Joshua Lockhart, Samuel Assefa, Manuela Veloso, Danilo Mandic (Imperial College), Tucker Balch
NeurIPS'19 Workshop on Robust AI in Financial Services, Vancouver, Canada, December 2019
@misc{https://doi.org/10.48550/arxiv.1911.12816,
doi = {10.48550/ARXIV.1911.12816},
url = {https://arxiv.org/abs/1911.12816},
author = {Mahfouz, Mahmoud and Filos, Angelos and Chtourou, Cyrine and Lockhart, Joshua and Assefa, Samuel and Veloso, Manuela and Mandic, Danilo and Balch, Tucker},
keywords = {Computational Finance (q-fin.CP), Trading and Market Microstructure (q-fin.TR), FOS: Economics and business, FOS: Economics and business},
title = {On the Importance of Opponent Modeling in Auction Markets}
publisher = {arXiv},
year = {2019},
copyright = {arXiv.org perpetual, non-exclusive license}
}
The dynamics of financial markets are driven by the interactions between participants, as well as the trading mechanisms and regulatory frameworks that govern these interactions. Decision makers would rather not ignore the impact of other participants on these dynamics, and should employ tools and models that take this into account. To this end, we demonstrate the efficacy of applying opponent-modeling in a number of simulated market settings. While our simulations are simplified representations of actual market dynamics, they provide an idealized “playground” in which our techniques can be demonstrated and tested. We present this work with the aim that our techniques could be refined and, with some effort, scaled up to the full complexity of real-world market scenarios. We hope that the results presented encourage practitioners to adopt opponent-modeling methods and apply them on live systems, in order to enable not only reactive but also proactive decisions to be made.
Generating Synthetic Data in Finance: Opportunities, Challenges and Pitfalls
Samuel Assefa, Danial Dervovic, Mahmoud Mahfouz, Tucker Balch, Prashant Reddy, Manuela Veloso
NeurIPS'19 Workshop on Robust AI in Financial Services, Vancouver, Canada, December 2019
@inproceedings{10.1145/3383455.3422554,
author = {Assefa, Samuel A. and Dervovic, Danial and Mahfouz, Mahmoud and Tillman, Robert E. and Reddy, Prashant and Veloso, Manuela},
title = {Generating Synthetic Data in Finance: Opportunities, Challenges and Pitfalls},
year = {2020},
isbn = {9781450375849},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3383455.3422554},
doi = {10.1145/3383455.3422554},
booktitle = {Proceedings of the First ACM International Conference on AI in Finance},
articleno = {44},
numpages = {8},
keywords = {synthetic data, privacy preserving data generation, simulation},
location = {New York, New York},
series = {ICAIF '20}
}
Financial services generate a huge volume of data that is extremely complex and varied. These datasets are often stored in silos within organisations for various reasons, including but not limited to, regulatory requirements and business needs. As a result, data sharing within different lines of business as well as outside of the organisation (e.g. to the research community) is severely limited. It is therefore critical to investigate methods for synthesising financial datasets that follow the same properties of the real data while respecting the need for privacy of the parties involved in a particular dataset. This introductory paper aims to highlight the growing need for effective synthetic data generation in the financial domain. We highlight three main areas of focus for the academic community: 1) Generating realistic synthetic datasets. 2) Measuring the similarities between real and generated datasets 3) Ensuring the generative process satisfies any privacy constraints. Although these challenges are also present in other domains, the extra regulatory and privacy requirements add another dimension of complexity and offer a unique opportunity to study the topic in financial services. Finally, we aim to develop a shared vocabulary and context for generating synthetic financial data using two types of financial datasets as examples.
SMPAI: Secure Multi-Party Computation for Federated Learning
Antigoni Polychroniadou, Vaikkunth Mugunthan (MIT), David Byrd (Georgia Institute of Technology), Tucker Balch
NeurIPS'19 Workshop on Robust AI in Financial Services, Vancouver, Canada, December 2019
@misc{https://doi.org/10.48550/arxiv.2010.05867,
doi = {10.48550/ARXIV.2010.05867},
url = {https://arxiv.org/abs/2010.05867},
author = {Byrd, David and Polychroniadou, Antigoni},
keywords = {Cryptography and Security (cs.CR), Artificial Intelligence (cs.AI), Multiagent Systems (cs.MA), General Finance (q-fin.GN), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Economics and business, FOS: Economics and business},
title = {Differentially Private Secure Multi-Party Computation for Federated Learning in Financial Applications},
publisher = {arXiv},
year = {2020},
copyright = {arXiv.org perpetual, non-exclusive license}
}
Federated Learning is a technique that enables a large number of users to jointly learn a shared machine learning model, managed by a centralized server, while the training data remains on user devices. That said, federated learning reduces data privacy risks. Privacy concerns still exist since it is possible to leak information about the training data set from the trained model’s weights or parameters. Most federated learning systems use the technique of differential privacy to add noise to the weights so that it is harder to reverse-engineer the individual data sets. Differential privacy reduces the risk but does not eliminate leakage from the data. The combination of differential privacy and cryprogrpahy can eliminate leakage. As opposed to prior works, we propose a new mechanism that protects against a wide range of attacks. Our mechanism is based on advanced cryptographic techniques, in particular, secure multiparty computation and differential privacy. Our model has been developed and tested on the ABIDES environment simulating mobile device networks.
Towards Explaining Exchange Traded Funds' Impact on Market Volatility Using an Agent-based Model
Megan J Shearer (University of Michigan), David Byrd (Georgia Institute of Technology), Tucker Balch
NeurIPS'19 Workshop on Robust AI in Financial Services, Vancouver, Canada, December 2019
Exchange traded funds (ETF), which are baskets of securities that trade on the stock market, have become a popular investment tool, but potentially increase the price co-movement of their underlying securities. We study index-based ETFs, because underlying securities trade on the same market as their corresponding ETF, which creates ample opportunities for traders to arbitrage between price deviations in the ETF and the market index. Considering the increase in market volatility in 2018 and 2019 in the US stock market, we examine if an ETF spreads mini flash crashes, or small volatility events, from one of its underlying symbols to another. We address this question in a simulated environment with an ETF and two symbols which compose the ETF’s portfolio. We explore two market environments, one with an ETF and arbitrage agents, and one without an ETF and arbitrage agents. We find that the presence of an ETF and arbitrage agents increases underlying symbols’ overall volatility, and when one symbol experiences a mini flash crash, the other symbol does experience a momentary price change in the opposite direction. This supports the idea that ETFs potentially increase market-wide volatility by spreading volatility events through their portfolios. To further this work, we hope to utilize learning to implement smarter arbitrage agents and smarter background agents who might avoid adverse selection by not trading during mini flash crashes.
AI pptX: Robust Continuous Learning for Document Generation with AI Insights
Vineeth Ravi, Sélim Amrouni, Andrea Stefanucci, Prashant Reddy, Manuela Veloso
NeurIPS'19 Workshop on Robust AI in Financial Services, Vancouver, Canada, December 2019
@unknown{unknown,
author = {Ravi, Vineeth and Amrouni, Selim and Stefanucci, Andrea and Reddy, Prashant and Veloso, Manuela},
year = {2020},
month = {10},
pages = {},
title = {AI pptX: Robust Continuous Learning for Document Generation with AI Insights}
}
Business analysts create billions of slide decks, reports and documents annually. Most of these documents have well-defined structure comprising of similar content generated from data. We present AI pptX, a novel AI framework for creating and modifying documents as well as extract insights in the form of natural language sentences from data. AI pptX has three main components: (i) a component that translates users’ natural language input into “skills” that encapsulate content editing and formatting commands, (ii) a robust continuously learning component that interacts with users, and (iii) a component that automatically generates hierarchical insights in the form of natural language sentences. We illustrate (i) and (ii) with a study of 18 human users tasked to create a presentation deck and observe the learning capability from a decrease in user-input commands by up to 45%. We demonstrate the robust learning capability of AI pptX with experimental simulations of non-collaborative users. We illustrate (i) and (iii) by automatically generating insights in natural language using a data set from the Electricity Transmission Network of France (RTE); we show that a complex statistical analysis of series can automatically be distilled into easily interpretable explanations called AI Insights
Nick Petosa (Georgia Institute of Technology), Tucker Balch
NeurIPS’19 Deep Reinforcement Learning Workshop, December 2019
@misc{https://doi.org/10.48550/arxiv.1910.13012,
doi = {10.48550/ARXIV.1910.13012},
url = {https://arxiv.org/abs/1910.13012},
author = {Petosa, Nick and Balch, Tucker},
keywords = {Artificial Intelligence (cs.AI), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Multiplayer AlphaZero},
publisher = {arXiv},
year = {2019},
copyright = {arXiv.org perpetual, non-exclusive license}
}
The AlphaZero algorithm has achieved superhuman performance in two-player, deterministic, zero-sum games where perfect information of the game state is available. This success has been demonstrated in Chess, Shogi, and Go where learning occurs solely through self-play. Many real-world applications (e.g., equity trading) require the consideration of a multiplayer environment. In this work, we suggest novel modifications of the AlphaZero algorithm to support multiplayer environments, and evaluate the approach in two simple 3-player games. Our experiments show that multiplayer AlphaZero learns successfully and consistently outperforms a competing approach: Monte Carlo tree search. These results suggest that our modified AlphaZero can learn effective strategies in multiplayer game scenarios. Our work supports the use of AlphaZero in multiplayer games and suggests future research for more complex environments.
Reinforcement Learning for Market Making in a Multi-agent Dealer Market
Sumitra Ganesh, Nelson Vadori, Mengda Xu, Prashant Reddy, Manuela Veloso
NeurIPS'19 Workshop on Robust AI in Financial Services, Vancouver, Canada, December 2019
@misc{https://doi.org/10.48550/arxiv.1911.05892,
doi = {10.48550/ARXIV.1911.05892},
url = {https://arxiv.org/abs/1911.05892},
author = {Ganesh, Sumitra and Vadori, Nelson and Xu, Mengda and Zheng, Hua and Reddy, Prashant and Veloso, Manuela},
keywords = {Trading and Market Microstructure (q-fin.TR), Machine Learning (cs.LG), Multiagent Systems (cs.MA), FOS: Economics and business, FOS: Economics and business, FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Reinforcement Learning for Market Making in a Multi-agent Dealer Market},
publisher = {arXiv},
year = {2019}
copyright = {arXiv.org perpetual, non-exclusive license}
}
Market makers play an important role in providing liquidity to markets by continuously quoting prices at which they are willing to buy and sell, and managing inventory risk. In this paper, we build a multi-agent simulation of a dealer market and demonstrate that it can be used to understand the behavior of a reinforcement learning (RL) based market maker agent. We use the simulator to train an RL-based market maker agent with different competitive scenarios, reward formulations and market price trends (drifts). We show that the reinforcement learning agent is able to learn about its competitor’s pricing policy; it also learns to manage inventory by smartly selecting asymmetric prices on the buy and sell sides (skewing), and maintaining a positive (or negative) inventory depending on whether the market price drift is positive (or negative). Finally, we propose and test reward formulations for creating risk averse RL-based market maker agents.
Get Real: Realism Metrics for Robust Limit Order Book Market Simulations
Svitlana Vyetrenko, David Byrd (Georgia Institute of Technology), Nick Petosa (Georgia Institute of Technology), Mahmoud Mahfouz, Danial Dervovic, Tucker Balch
NeurIPS'19 Workshop on Robust AI in Financial Services, Vancouver, Canada, December 2019
@article{https://doi.org/10.48550/arxiv.1912.04941,
doi = {10.48550/ARXIV.1912.04941},
url = {https://arxiv.org/abs/1912.04941},
author = {Vyetrenko, Svitlana and Byrd, David and Petosa, Nick and Mahfouz, Mahmoud and Dervovic, Danial and Veloso, Manuela and Balch, Tucker Hybinette},
keywords = {Trading and Market Microstructure (q-fin.TR), Multiagent Systems (cs.MA), FOS: Economics and business, FOS: Economics and business, FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Get Real: Realism Metrics for Robust Limit Order Book Market Simulations},
publisher = {arXiv},
year = {2019},
copyright = {arXiv.org perpetual, non-exclusive license}
}
Machine learning (especially reinforcement learning) methods for trading are increasingly reliant on simulation for agent training and testing. Furthermore, simulation is important for validation of hand-coded trading strategies and for testing hypotheses about market structure. A challenge, however, concerns the robustness of policies validated in simulation because the simulations lack fidelity. In fact, researchers have shown that many market simulation approaches fail to reproduce statistics and stylized facts seen in real markets. As a step towards addressing this we surveyed the literature to collect a set of reference metrics and applied them to real market data and simulation output. Our paper provides a comprehensive catalog of these metrics including mathematical formulations where appropriate. Our results show that there are still significant discrepancies between simulated markets and real ones. However, this work serves as a benchmark against which we can measure future improvement.
*Equal contribution by the authors
This [paper/presentation] was prepared for informational purposes by the [Artificial Intelligence Research] group of JPMorgan Chase & Co and its affiliates (“JP Morgan”), and is not a product of the Research Department of JP Morgan. JP Morgan makes no representation and warranty whatsoever and disclaims all liability, for the completeness, accuracy or reliability of the information contained herein. This document is not intended as investment research or investment advice, or a recommendation, offer or solicitation for the purchase or sale of any security, financial instrument, financial product or service, or to be used in any way for evaluating the merits of participating in any transaction, and shall not constitute a solicitation under any jurisdiction or to any person, if such solicitation under such jurisdiction or to such person would be unlawful.
You're now leaving J.P. Morgan
J.P. Morgan’s website and/or mobile terms, privacy and security policies don’t apply to the site or app you're about to visit. Please review its terms, privacy and security policies to see how they apply to you. J.P. Morgan isn’t responsible for (and doesn’t provide) any products, services or content at this third-party site or app, except for products and services that explicitly carry the J.P. Morgan name.