Timezone: »

Posters and Open Discussions (see below for poster titles)
Ramya Malur Srinivasan · Miguel Perez · Yuanyuan Liu · Ben Wood · Dan Philps · Kyle Brown · Daniel Martin · Mykola Pechenizkiy · Luca Costabello · Rongguang Wang · Suproteem Sarkar · Sangwoong Yoon · Zhuoran Xiong · Enguerrand Horel · Zhu (Drew) Zhang · Ulf Johansson · Jonathan Kochems · Gregory Sidier · Prashant Reddy · Lana Cuthbertson · Yvonne Wambui · Christelle Marfaing · Galen Harrison · Irene Unceta Mendieta · Thomas Kehler · Mark Weber · Li Ling · Ceena Modarres · Abhinav Dhall · Arash Nourian · David Byrd · Ajay Chander · Xiao-Yang Liu · Hongyang Yang · Shuang (Sophie) Zhai · Freddy Lecue · Sirui Yao · Rory McGrath · Artur Garcez · Vangelis Bacoyannis · Alexandre Garcia · Lukas Gonon · Mark Ibrahim · Melissa Louie · Omid Ardakanian · Cecilia Sönströd · Kojin Oshiba · Chaofan Chen · Suchen Jin · aldo pareja · Toyo Suzumura
  1. Clustering and Learning from Imbalanced Data
  2. Deep Hedging: Hedging Derivatives Under Generic Market Frictions Using Reinforcement Learning
  3. Generating User-friendly Explanations for Loan Denials using GANs
  4. Practical Deep Reinforcement Learning Approach for Stock Trading
  5. Idiosyncrasies and challenges of data driven learning in electronic trading
  6. Machine learning-aided modeling of fixed income instruments
  7. An Interpretable Model with Globally Consistent Explanations for Credit Risk
  8. Continuous learning augmented investment decisions
  9. HELOC Applicant Risk Performance Evaluation by Topological Hierarchical Decomposition
  10. Looking Deeper into the Deep Learning Models: Attribution-based Explanations of TextCNN
  11. Matrix Regression and Its Applications in Cryptocurrency Trading
  12. Sensitivity based Neural Networks Explanations
  13. On the Need for Fairness in Financial Recommendation Engines
  14. Read the News, not the Books: Predicting Firms’ Financial Health

Author Information

Ramya Malur Srinivasan (Fujitsu Laboratories of America)
Miguel Perez (Ernst and Young LLP)

I'm a data scientist at a Financial Services Organization focused on developing algorithms and optimizations to crowdsource subject matter experts' evaluation of risk for anti-money laundering and employee conduct, and developing graph convolution neural networks and statistical learning models for studying behavior captured in banking customers' transaction records. The teams that I work with and oversee are applying these supervised and unsupervised models on graph databases of Global Forbes 500 banking transaction records. My academic background is in mathematical physics as an expert in Quantum Algorithmic Complexity, Category and Topos Theory, and quantum foundations. My research interests focus on (1) applying information theory to decision systems for algorithmic optimization, (2) applications of rating-ranking algorithms with geometric and non-trivial loss functions, (3) critical phenomenon on time varying graphs.

Yuanyuan Liu (AIG)
Ben Wood (JP Morgan)
Dan Philps (City, University of London. Rothko Investment Strategies)

Dan Philps is a Computer Scientist, head of Rothko Investment Strategies and is an artificial intelligence (AI) researcher. He has 20 years of quantitative investment experience. Prior to Rothko, he was a senior fund manager at Mondrian Investment Partners. Before 1998, Philps worked as an analyst/programmer at a number of investment banks, specializing in trading and risk models. He has a BSc (Hons) from King’s College London, is a CFA charterholder, a member of CFA Society of the UK and holds a post graduate research role at City, London University.

Kyle Brown (Wright State University)
Daniel Martin (Carnegie Mellon University)
Mykola Pechenizkiy (TU Eindhoven)
Luca Costabello (Accenture Labs)
Rongguang Wang (Cornell University)
Suproteem Sarkar (Harvard University)
Sangwoong Yoon (Seoul National University)
Zhuoran Xiong (Columbia University)
Enguerrand Horel (Stanford University)
Zhu (Drew) Zhang (Iowa State University)
Ulf Johansson (Jönköping University)
Jonathan Kochems (JP Morgan)
Gregory Sidier (JP Morgan)
Prashant Reddy (J.P. Morgan)
Lana Cuthbertson (ATB Financial)
Yvonne Wambui (Carnegie Mellon University)
Christelle Marfaing (Lydia Solutions)
Galen Harrison (University of Chicago)
Irene Unceta Mendieta (BBVA Data & Analytics)
Thomas Kehler (CrowdSmart)

Tom Kehler is President, Chief Scientist, and Co-Founder at CrowdSmart; a technology-based investment company dedicated to transforming seed investing and radically improving outcomes for investors and startups. Dr. Kehler has over 30 years of experience as an entrepreneur and CEO. He was CEO of InelliCorp the first AI/Expert Systems Company to go public. He was CEO of Connect one of the first ecommerce companies to go public. He was CEO of Recipio, an early social marketing company that enabled large scale brainstorming between companies and their customers. Recipio’s customers included LEGO, NBC, and Procter & Gamble. Recipio was sold to Informative where he later because CEO. Informative was sold to Satmetrix where he headed up Community Solutions. After Satmetrix, Dr. Kehler was one of the founders of ClearStreet, a fintech company. Dr. Kehler has served on the Information Technology Advisory Board of the National Research Council. He has served on various corporate, academic, and non-profit boards. Dr. Kehler received a Ph.D. in applied physics from Drexel University and has over 20 publications in artificial intelligence, natural language processing, and physics. Currently he is focused on predictive analytics models for startups.

Mark Weber (MIT-IBM Watson AI Lab)

Mark Weber (@markrweber) is a research scientist at the MIT-IBM Watson AI Lab, a $240 million academic-industry partnership for the responsible advancement of artificial intelligence. Trained in finance, economics, and integrated thinking, Mark’s expertise is connecting dots across disciplines to bridge academic research with real-world applications. # Scalable deep learning for anti-money laundering (AML) Mark’s current MIT-IBM research involves an emerging sub-field of AI - graph convolutional networks - and builds on the breakthrough work of Jie Chen (IBM Research) with FastGCN. Teaming up with Charles Leiserson’s high performance computing group at MIT CSAIL, Mark and company aspire to create new AI tools for anti-money-laundering (AML) to fight financial crime, such as the $40 billion human trafficking industry. # b_verify: a blockchain protocol for supply chain finance While doing his graduate work in finance at MIT Sloan, Mark worked as a researcher at the the MIT Media Lab with the Digital Currency Initiative. There he led the development of b_verify, an open-source protocol for supply chain finance utilizing public blockchains and Internet-of-Things (IoT). The project grew out of an engagement with the Mexican government and the Inter-American Development Bank, receiving funding from the latter as well as from the MIT Legatum Center for Entrepreneurship and Development. Focused on warehouse receipts in agricultural supply chains as an informing use-case, the b_verify protocol presents innovations in both computer science — scalable non-equivocation using public blockchains — and management science — predicted improvements in credit access via inventory transaction signaling and asset-backed lending (among other benefits). View the b_verify code on Github. Contact Mark if you are interested in utilizing the protocol.

Li Ling (JP Morgan Chase)
Ceena Modarres (Capital One)
Abhinav Dhall (Indian Institute of Technology Ropar)
Arash Nourian (UC Berkeley)
David Byrd (Georgia Institute of Technology)
Ajay Chander (Fujitsu Labs of America)
Xiao-Yang Liu (Columbia University)
Hongyang Yang (Columbia University)
Shuang (Sophie) Zhai (Iowa State University)
Freddy Lecue (INRIA)
Sirui Yao (Virginia Polytechnic Institute and State University)
Rory McGrath (Accenture Labs)
Artur Garcez (City, University of London)
Vangelis Bacoyannis (J.P. Morgan)
Alexandre Garcia (Telecom ParisTech)
Lukas Gonon (ETH Zurich)
Mark Ibrahim (Capital One, Center for Machine Learning)

Mark Ibrahim is a senior machine learning engineer with a background in mathematics, deep learning, and knowledge graphs. He has worked on methods to interpret neural network predictions and applications of deep learning to forecasting. He enjoys good coffee, eating well, and editing text in Vim.

Melissa Louie (Capital One)
Omid Ardakanian (University of Alberta)
Cecilia Sönströd (University of Borås)
Kojin Oshiba (Harvard College)
Chaofan Chen (Duke University)
Suchen Jin (J.P. Morgan)
aldo pareja (IBM)
Toyo Suzumura (IBM Thomas J. Research Center)

More from the Same Authors