2020


AI to Eradicate Financial Crime

Tom Goldstein

University of Maryland, College Park, Robust, Private and Fair ML for Financial Models

A. Erdem Sariyuce

University at Buffalo, Detecting Fraudulent Transactions in Online Marketplaces Using Temporal Network Motifs

Austin R Benson

Cornell University, Pattern-based Heterogeneous Graph Clustering at Scale

Furong Huang

University of Maryland, College Park, Robust, Private and Fair ML for Financial Models

Rok Sosic

Stanford University, ROLAND: Representation Learning and Anomaly Detection in Financial Networks

Leandros Tassiulas

Yale University, Distributed Ledgers for Enhancing the Trust and Performance of Financial Networks

Naoki Masuda

University at Buffalo, Detecting Fraudulent Transactions in Online Marketplaces Using Temporal Network Motifs

Jure Leskovec

Stanford University, ROLAND: Representation Learning and Anomaly Detection in Financial Networks

AI to Liberate Data Safely

Fabio Caccioli

University College London, Network Methods for the Generation of Synthetic Datasets

Huijia Lin

University of Washington, Secure Data Analytics with a Single Untrusted Server

Tal Malkin

Columbia University, MAGIC: Machine Learning Through a Cryptographic Len

Elaine Shi

Cornell University, CryptML: Cryptographic Machine Learning

Rafail Ostrovsky

UCLA, SECURE: SEcure CompuUtation for fRaud dEtection

Rafael Pass

Cornell University, CryptML: Cryptographic Machine Learning

Daniela Rus

MIT CSAIL, Secure Private Computing Using Coresets

Giulia Fanti

Carnegie Mellon University, Producing Privacy-Preserving, Synthetic Time Series Datasets with Generative Adversarial Networks

Yan Liu

University of Southern California, HR-Neural ODE: Multivariate Multiresolution Time Series Synthesizer via Neural Ordinal Differential Equations

Yarin Gal

University of Oxford, Uncertainty Aware Data-driven Generative Models and Multi-agent Simulators

Stefano Tessaro

University of Washington, Secure Data Analytics with a Single Untrusted Server

Rachel Cummings

Georgia Tech, Differentially Private Synthetic Data Generation

Vyas Sekar

Carnegie Mellon University, Producing Privacy-Preserving, Synthetic Time Series Datasets with Generative Adversarial Networks

AI to Predict and Affect Economic Systems

Henry Lam

Columbia University, Calibrating Large-Scale Simulation Models via Distributionally Robust Optimization

Michael Wellman

University of Michigan, Multiagent Modeling of the Financial Payments System

Michael Barr

University of Michigan, Multiagent Modeling of the Financial Payments System

Gabriel Rauterberg

University of Michigan, Multiagent Modeling of the Financial Payments System

Chelsea Finn

Stanford University, Continuous Meta-Reinforcement Learning in Non-Stationary Environments

Michael Wooldridge

Oxford University, Opponent Modeling in Adaptive Markets

Fernando Fernández

Universidad Carlos III de Madrid, Learning Similarity Metrics Between Simulation and the Real World

Sarit Kraus

Bar-Ilan University, Agents Supporting Large-scale Environments of Teams of People and Computer Systems –Y2

Sergey Levine

UC Berkeley, Multi-Agent Modeling with Inverse RL and POMDP Models

Uday Rajan

University of Michigan, Multiagent Modeling of the Financial Payments System

AI to Move Employees Up the Value Chain

Yun Fu

Northeastern University, Reinforced Graph-Structured Expert Model for Business Intelligence

Reid Simmons

Carnegie Mellon University, Timely Suggestions for Improving Data Analyst Cognitive Workflows

William Yang Wang

UC Santa Barbara, Combining Knowledge Base and Unstructured Text for Open-Domain Financial Question Answering

Craig Knoblock

University of Southern California, Supporting Cognitive Workflows with Hybrid Knowledge Graphs

Kamalakar Karlapalem

IIIT Hyderabad, Guided Discovery of Cognitive Steps within a Task

Jay Pujara

University of Southern California, Supporting Cognitive Workflows with Hybrid Knowledge Graphs

Stephanie Rosenthal

Carnegie Mellon University, Timely Suggestions for Improving Data Analyst Cognitive Workflows