Jingbo (Eric) Yang

Making Better Markets for a Better World

Stanford AI for Healthcare

About Me

I am Eric (Jingbo), a quantitative minion at Citadel Securities. I am interested in all things machine learning, let it be modeling, pipelining, or data scraping. Before joining Citadel Securities, I was a CS Masters student Stanford University and an active member of the Stanford AI for Healthcare bootcamp. Before that, I completed my BASc. of Electrical and Computer Engineering from University of Toronto.

While at school, I've had a few internships and have taken part in many research projects. Oh, also, I built rockets! I'm sure few software engineers have worked on computational fluid dynamics modeling for oxidizer injector plate and rocket airframe.

Education

Master of Science in Computer Science

Stanford University

2018.09 - 2020.06
Bachelor of Appliced Science in Engineering Science

University of Toronto

2013.09 - 2018.06

Work Experience

Citadel Securities

Quantitative Minion

2020.08-Present

Forex, until 202303.
Now: Alpha/strat research.

Citadel

Software Engineer Intern

2019.06-2019.08

Equities front office data engineering.
Intelligent financial statement analysis.

Stanford University

Research Assisstant

2018.01-2020.08

EEG analysis for depression.
Self-supervised learning for chest X-ray.
Driver identification from driving behaviour.

Intel PSG (former Altera)

Software Engineer Intern

2016.05-2017.04

FPGA device property management and simulation.
Optimization for device compilation process.
C++ compiler migration.

Rocscience

Software Engineer Intern

2015.05-2015.08

Geological data management.
3D geometry error analysis.

Publications

MoCo-CXR: Self-supervised contrastive learning for chest X-ray interpretation

Hari Sowrirajan, Jingbo Yang , Andrew Ng, Pranav Rajpurkar

ACM Conference on Health, Inference, and Learning (CHIL) Workshop, 2021

Medical Imaging with Deep Learning (MIDL), 2021

Preprint

Driver2vec: Driver Identification from Automotive Data

Jingbo Yang, Ruge Zhao, Meixian Zhu, David Hallac, Jaka Sodnik, Jure Leskovec

KDD Mining and Learning from Time Series Workshop (MiLeTS), August 2020

Paper Source Sample Dataset

Evaluation of a Machine Learning Model Based on Pretreatment Symptoms and Electroencephalographic Features to Predict Outcomes of Antidepressant Treatment in Adults With Depression

Pranav Rajpurkar, Jingbo Yang, Nathan Dass, Vinjai Vale, Arielle S Keller, Jeremy Irvin, Zachary Taylor, Sanjay Basu, Andrew Ng, Leanne M Williams

JAMA Network Open Psychiatry, June 2020

Paper