Yuwen Zhang
Open to work4 years experienceData Scientist
Data Scientist with experience in production-grade data pipelines, statistical forecasting, and automated analytics.
Standing Rank
Rank Not Available
Developer Badges
Skills & Technologies
28 skillsGitHub Activity Evidence
GitHub Footprint Not Connected
Recruiters value verified code contributions. Linking a GitHub account displays live heatmaps, active contribution metrics, repository languages, and push activity tags.
Work Experience
Senior Quantitative Trading Associate
Five Dimensions Energy LLC
- Lead the execution of data-driven workflows supporting the expansion of load operations into ISO-NE, coordinating cross-functional deliverables and ensuring production readiness of analytics pipelines
Quantitative Trading Associate
Five Dimensions Energy LLC
- Developed Python ETL workflows for API-based and web-scraped ISO and utility data (PJM, CAISO, ERCOT, ISO-NE), including data cleaning and normalization, with downstream data management in SQL
- Designed regression-based energy volume forecasting models incorporating weather and calendar variables; validated model performance through back-testing with MAPE under 5% and generated 20-year weather-normalized datasets for long-term load volume forecasting
- Build and evaluated Dense-LSTM models for energy price forecasting in virtual trading; explored transformer-based models (FinBERT, TimesFM), generating around $100k in pilot-phase revenue
- Implemented automated forecast calibration workflows comparing realized and nominated loads over rolling 30-day window, reducing the cost of forecasting errors from $0.28/MWh to $0.13/MWh
- Architected SQL Server-driven automation pipelines supporting daily energy serving operational analytics, including forecasting, back-casting, and invoicing outputs
- Developed an end-to-end nomination and awarded bid download pipeline, designed 100+ automated tasks leveraging PJM APIs, generating more than $10 million in annual PnL
- Participated in FTR and ARR auctions, assessing load-serving risk exposure and executing FTR hedging strategies; actively managed the ARR portfolio to capture over $2 million in upside value
- Built and implemented a virtual bidding framework in ERCOT; leveraging ERCOT APIs for automated bidding and applying portfolio analysis to optimize bidding strategies
Summer Trading Analyst
Five Dimensions Energy LLC
- Built data visualization and reporting solutions to analyze weather, price, and volume trends; implemented an XLWings-based reporting pipeline to deliver trader-accessible analytics
Data Science Project Coordinator
Rights CoLab
- Studied the financial materiality of labor rights, focusing on labor conditions and supply chains
- Developed website scrappers using Selenium WebDriver to automatically extract articles from FactSet’s TruValue SASB Spotlight DataFeed, shareholder resolutions, and earnings call transcripts
- Applied TF-IDF, clustering, sentiment analysis and co-occurrence matrices to extract themes from unstructured text
- Designed few-shot GPT prompting workflows to accelerate text extraction and proposed additional ESG metrics aligned with SASB materiality standards
Projects
Projects Not Populated
Personal applications, open-source work, and code repos will show here.
Leaderboard Standings
Leaderboard Position Pending
Global test scores, peer standing percentiles, and algorithm leaderboard ranks are updated dynamically.
Assessment Highlights
Assessments Not Completed
Coding evaluations, system assessment results, and conceptual score badges will appear here after taking a test.
AI Collaboration Score
AI Collaboration Score Pending
Developer coding behavior, assistant cooperation, and AI pair-programming indicators are evaluated during live coding sessions.
Role Compatibility Profile
Role Compatibility Analysis Pending
Custom matching reports, candidate role compatibility percentiles, and core engineer strength profiles are processed once conceptual code screenings are complete.
Achievements
Energy Price Forecasting Revenue
Generated around $100k in pilot-phase revenue through Dense-LSTM models for energy price forecasting.
Forecasting Error Reduction
Reduced the cost of forecasting errors from $0.28/MWh to $0.13/MWh.
Annual PnL Generation
Generated more than $10 million in annual PnL through automated nomination and awarded bid download pipeline.
ARR Portfolio Value Capture
Captured over $2 million in upside value through ARR portfolio management.
About Details
Professional Bio
Data Scientist with extensive experiences in building production-grade data pipelines, statistical forecasting models, and automated analytics systems. Proven ability to design Python- and SQL-based ETL workflows, develop and calibrate regression and deep learning models.
Master of Science in Data Science
Columbia University (2021 - 2022)
Bachelor of Science in Data Science, Mathematics of Finance and Risk Management (Double Major)
University of Michigan-Ann Arbor (2017 - 2021)