Yiyu Huang
Data scientist/Data engineer
Summary
Adept at leveraging Python Programming and fostering team growth, spearheaded high-impact ETL projects at Gientech, boosting anti-money laundering model recall to 86%. Tenure across various sectors, including healthcare and technology, underscores ability to deliver revenue-generating data solutions and mentorship, showcasing a blend of technical prowess and leadership.
Overview
8
8
years of professional experience
8
8
years of post-secondary education
Work History
Data Analysis and Mining Consultant/Development Engineer
Gientech
9 2019 - Current
- Led end-to-end implementation of multiple high-impact ETL projects (Money laundering and optimization bank customer service) using Spark and Airflow from requirements gathering through deployment and post-launch support stages.
- Refined Anti-money laundering model by enhancing feature engineering and using model ensemble, recall increase from 80% to 86% and covered 90% of high-risk cases.
- Reengineered existing ETL workflows to improve performance by identifying bottlenecks and optimizing code accordingly, ETL runtime reduce by 60%.
- Developed automatic data quality validation pipeline which is adopted by multiple project teams.
- Mentored junior engineers on best practices in data engineering, fostering a culture of continuous learning and improvement within the team.
Research Analyst/Research Assistant
Shanghai Suvalue healthcare technology company
04.2019 - 09.2019
- Responsible for data analysis project management, analytic plan design and performing in-depth analysis.
- Successfully delivered three medical data analysis projects within three months, generating 1 million RMB in revenue for the company.
Data Analysis and Product Construction
Foxconn technology group
05.2018 - 12.2018
- Designed and construct data analysis product with engineering team and business team, data analysis platform was successfully built which can be used for e-commerce users’ portrait analysis and operation analysis.
- Communicated effectively with team members to deliver updates on project milestones and deadlines.
Informatics Analyst
SCAN health plan
11.2016 - 11.2017
- Helped businesses to solve various problems and provided data research support through statistical analysis and econometric analysis methods.
- Managed data analysis projects, regularly generated data reports using SAS and Python for business needs, and provided data insights for business decision-making.
- By building re-admission risk model, reduced hospitalization expenses by 3000 US dollar per person for the hospital.
Education
Master of Science - Finance
The Chinese University of Hong Kong
Shenzhen 09.2021 - 07.2023
Master of Science - Pharmaceutical Economics And Policy
University of Southern California
Los Angeles 08.2014 - 08.2016
Bachelor of Science - Bioengineering
Guangzhou University
Guangzhou 09.2009 - 06.2013
Skills
Python Programming
Machine Learning
Statistical Analysis
Spark
GCP
Hadoop Ecosystem
Data Mining
Data Pipeline Design
Scala
SQL
Data Management
Accomplishments
Ranked in the top 0.5% in the 2024 TradingView Lead August Portfolio Competition
Additional Information
Utilizing the LightGBM models to build a equities quantitative trading model on AWS, the out-of-sample backtesting results show a cumulative return of over 100% in 90 days, a Sharpe ratio exceeding 5, and a maximum daily drawdown of 7%
Timeline
Master of Science - Finance
The Chinese University of Hong Kong
09.2021 - 07.2023
Research Analyst/Research Assistant
Shanghai Suvalue healthcare technology company
04.2019 - 09.2019
Data Analysis and Product Construction
Foxconn technology group
05.2018 - 12.2018
Informatics Analyst
SCAN health plan
11.2016 - 11.2017
Master of Science - Pharmaceutical Economics And Policy
University of Southern California
08.2014 - 08.2016
Bachelor of Science - Bioengineering
Guangzhou University
09.2009 - 06.2013
Data Analysis and Mining Consultant/Development Engineer
Gientech
9 2019 - Current
Similar Profiles
Kamudurai SakthivelKamudurai Sakthivel
Automation Test Manager/Lead at GienTechAutomation Test Manager/Lead at GienTech
Maggie (Bingjie) ChenMaggie (Bingjie) Chen
Account Manager - B2B Business Development at GienTechAccount Manager - B2B Business Development at GienTech
Martin MichaudMartin Michaud
Freelance Translator at Smartcat, Transcom, Commnicaid, Gientech, Janus...Freelance Translator at Smartcat, Transcom, Commnicaid, Gientech, Janus...