publications

2025

  1. Entropy-Aware Branching for Improved Mathematical Reasoning
    Xianzhi Li, Ethan Callanan, Xiaodan Zhu, Mathieu Sibue, Antony Papadimitriou, Mahmoud Mahfouz, Zhiqiang Ma, and Xiaomo Liu
    arXiv preprint arXiv:2503.21961, 2025

2024

  1. Capacity planning and scheduling for jobs with uncertainty in resource usage and duration
    Sunandita Patra, Mehtab Pathan, Mahmoud Mahfouz, Parisa Zehtabi, Wided Ouaja, Daniele Magazzeni, and Manuela Veloso
    The Journal of Supercomputing, 2024
  2. The State of the Art of Large Language Models on Chartered Financial Analyst Exams
    Mahmoud Mahfouz, Ethan Callanan, Mathieu Sibue, Antony Papadimitriou, Zhiqiang Ma, Xiaomo Liu, and Xiaodan Zhu
    In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track, 2024

2023

  1. Method and system for providing dynamic workspace scheduler
    Parisa Zehtabi, Alberto Pozanco, Rui Manuel Ramos Teixeira Da SILVA, Salwa Husam Alamir, Daniel Borrajo, Mahmoud Mahfouz, Daniele Magazzeni, Maria Manuela Veloso, Tracy Rasco, Amy BLACKWELL, and others
    Apr 2023
    US Patent App. 17/450,609
  2. FinRDDL: Can AI planning be used for quantitative finance problems?
    Sunandita Patra, Mahmoud Mahfouz, Sriram Gopalakrishnan, Daniele Magazzeni, and Manuela Veloso
    FinPlan, Apr 2023
  3. Method and system for solving reconciliation tasks by integrating clustering and optimization
    Parisa Zehtabi, Mahmoud Mahfouz, Daniel Borrajo, Daniele Magazzeni, Manuela Veloso, Yufei Wu, Allan Anzagira, Sunandita Patra, Jonathan Roger Horn, Tracy Rasco, and others
    Nov 2023
    US Patent App. 17/661,211
  4. Towards Asset Allocation Using Behavioural Cloning and Reinforcement Learning
    Mahmoud Mahfouz, Sriram Gopalakrishnan, Miguel Suau, Sunandita Patra, Danilo Mandic, Daniele Magazzeni, and Manuela Veloso
    In AAAI Bridge: AI for Financial Services: https://sites.google.com/view/aaai-ai-fin/home, Nov 2023

2022

  1. System and method for institutional risk identification using automated news profiling and recommendation
    Mahmoud Mahfouz, Brian O’toole, Danny Schwartzman, Armineh Nourbakhsh, and Sameena Shah
    Sep 2022
    US Patent App. 17/654,843
  2. Towards Robust Representation of Limit Orders Books for Deep Learning Models
    Yufei Wu, Mahmoud Mahfouz, Daniele Magazzeni, and Manuela Veloso
    arXiv preprint arXiv:2110.05479, Sep 2022

2021

  1. How Robust are Limit Order Book Representations under Data Perturbation?
    Yufei Wu, Mahmoud Mahfouz, Daniele Magazzeni, and Manuela Veloso
    In ICML 2021 Workshop on Representation Learning for Finance and E-Commerce Applications. arXiv preprint: 2110.04752, Sep 2021
  2. A Framework for Institutional Risk Identification using Knowledge Graphs and Automated News Profiling
    Mahmoud Mahfouz, Armineh Nourbakhsh, and Sameena Shah
    arXiv preprint arXiv:2109.09103, Sep 2021
  3. Learning to Classify and Imitate Trading Agents in Continuous Double Auction Markets
    Mahmoud Mahfouz, Tucker Balch, Manuela Veloso, and Danilo Mandic
    In ACM International Conference on AI in Finance (ICAIF-2021), Sep 2021

2020

  1. Generating synthetic data in finance: opportunities, challenges and pitfalls
    Samuel Assefa, Danial Dervovic, Mahmoud Mahfouz, Tucker Balch, Prashant Reddy, and Manuela Veloso
    In ACM International Conference on AI in Finance (ICAIF-2020), Sep 2020

2019

  1. Compression and interpretability of deep neural networks via tucker tensor layer: From first principles to tensor valued back-propagation
    Giuseppe G Calvi, Ahmad Moniri, Mahmoud Mahfouz, Qibin Zhao, and Danilo P Mandic
    arXiv preprint arXiv:1903.06133, Sep 2019
  2. How to Evaluate Trading Strategies: Single Agent Market Replay or Multiple Agent Interactive Simulation?
    Tucker Hybinette Balch, Mahmoud Mahfouz, Joshua Lockhart, Maria Hybinette, and David Byrd
    In ICML 2019 Workshop on AI in Finance: Applications and Infrastructure for Multi-Agent Learning, Sep 2019
  3. On the Importance of Opponent Modeling in Auction Markets
    Mahmoud Mahfouz, Angelos Filos, Cyrine Chtourou, Joshua Lockhart, Samuel Assefa, Manuela Veloso, Danilo Mandic, and Tucker Balch
    In NeurIPS 2019 Workshop on Robust AI in Financial Services: Data, Fairness, Explainability, Trustworthiness, and Privacy, Sep 2019
  4. Get Real: Realism Metrics for Robust Limit Order Book Market Simulations
    Svitlana Vyetrenko, David Byrd, Nick Petosa, Mahmoud Mahfouz, Danial Dervovic, Manuela Veloso, and Tucker Hybinette Balch
    In NeurIPS 2019 Workshop on Robust AI in Financial Services: Data, Fairness, Explainability, Trustworthiness, and Privacy, Sep 2019