Portfolio
Technical & Data Science Projects
Featured Tutorial Projects
| Project | Description | Tools / Skills Utilized | View / Details |
|---|---|---|---|
| Build Your Own LinkedIn Analytics (2025 – 2026) | An end-to-end data product for personal LinkedIn Analytics, detailed for educational purposes in an ongoing blog series | Databricks, Python, Spark, SQL, Data Engineering, Data Analytics, Data Architecture, Dashboarding, Technical Documentation | Article Archive GitHub Repository |
Metis Data Science Bootcamp (2020): Project Portfolio
A comprehensive portfolio of end-to-end projects completed during the Metis Data Science Bootcamp (2020), demonstrating practical technical depth across machine learning, NLP, deep learning, and data engineering:
| Project | Description | Key Technologies | View / Details |
|---|---|---|---|
| NYC MTA Turnstile Data Analysis | Exploratory data analysis, station usage patterns, recommendation system for optimal campaign placement | Python, Pandas, Seaborn | Project Overview |
| MyAnimeList Score Prediction | Web scraping, feature engineering, regression modeling, and bias analysis for crowd-sourced entertainment | Python, Scikit-learn, BeautifulSoup | Project Overview |
| Global Fishing Watch Classification | Classification of maritime traffic, supervised ML for vessel activity using Random Forest (F1=0.90, AUC=0.98) | Python, PostgreSQL, Random Forest | Project Overview |
| Fake News Detection (LIAR Dataset) | Advanced NLP, topic modeling, and word embeddings for automated fact-checking and claim classification | Python, NLP, GloVe, LDA | Project Overview |
| Generative Poetry with LSTM Neural Nets | Deep learning model for creative text generation, full-stack integration with Flask and PostgreSQL | Python, Keras, LSTM, Flask | Project Overview |
- Full project list: Metis Bootcamp Projects Collection
Featured Product & UX Projects
| Project | Description | Tools / Skills Utilized | View / Details |
|---|---|---|---|
| Klook Travel Planner Capstone (2025) | End-to-end UX research and Figma prototyping, developed as part of the NTU Advanced Certificate in UI/UX & Digital Product Management | Figma, UX Research, Product Design | Figma Deck (Read-Only) |
- These projects showcase how UI/UX principles inform my approach to building intuitive, effective data products—reflecting my belief that real value emerges when technical excellence meets user-centric design.
Enterprise Data & AI Solutioning (Selected Work Summaries)
Prudential (Singapore) — Senior Data Engineer, Solutioning & Architecture
- Established medallion architecture and standardized cross-team documentation for scalable data lakehouse infrastructure.
- Led proof-of-concept and solutioning for GenAI and MLOps workflows, delivering increased operational efficiency and cost reduction.
- Guided technical development of AI/ML projects on Google Cloud and Databricks.
SPH Media — Lead Data Engineer
- Architected and delivered cost-saving, resilient data pipelines in AWS; implemented robust batch and streaming data solutions.
- Drove team-wide technical upskilling, process improvement, and documentation standardization.
- Managed analytics platform migration and integration for enterprise media operations.
How to Verify & Learn More
- Comprehensive certifications, with public verification links: Credentials & Verification
- Digital business card and latest contact: bit.ly/m/yzouyang
- LinkedIn profile: linkedin.com/in/yzouyang
For further detail or code samples, selected repositories or extended case studies are available upon request. Please use the above contact methods for access.