About me
Hi, I’m Chenyi Weng — a curious problem solver and data storyteller currently pursuing my Master’s in Spatial Data Science at the University of Southern California (expected Dec 2025).
My journey started with a BBA in International Business and a minor in Information Management, where I built a strong foundation in global trade, finance, and data management. Along the way, I realized that the real power lies in how we transform raw data into insights that influence decisions. That realization led me to combine my business background with advanced technical skills, bridging the gap between strategic thinking and data-driven execution.
At USC, I’ve sharpened my expertise in machine learning, scalable systems, and interactive data visualization. From building classification pipelines that achieve 95%+ accuracy to designing Spark-powered data extraction frameworks that handle millions of records, I enjoy translating complex data challenges into scalable, impactful solutions. My projects range from deep learning for image/audio analysis to interactive dashboards that empower decision-making — all rooted in a passion for using technology to solve real-world problems.
Technically, I’m fluent in Python (Flask, FastAPI, scikit-learn, TensorFlow, Keras), JavaScript (React, Node.js), SQL/NoSQL, and cloud computing with AWS/Docker, and I thrive at the intersection of software engineering and data science.
Beyond the code, what drives me is impact. I aspire to contribute to teams where I can turn messy, large-scale data into actionable insights and build applications that scale, especially in domains like urban systems, business intelligence, and AI-driven products.
If you’re looking for someone who blends business acumen with technical depth — and who genuinely enjoys the challenge of building things that matter — I’d love to connect.
What i'm doing
-
Full-Stack & Cloud Development
Experience with React, Node.js, PostgreSQL, and CI/CD; skilled in building interactive dashboards and APIs.
-
Machine Learning & AI Development
Built ML pipelines (Logistic Regression, Random Forest, SVM, CNNs) with >95% accuracy on structured, image, and audio datasets.
-
Data Visualization & Analytics
Designed dashboards with Plotly/Dash for million-scale datasets with filtering and drill-down features.
-
Scalable Data Systems
Developed Python + Spark pipeline for large-scale data extraction and cleaning, achieving >90% data accuracy.