Skip to content
View MONA100421's full-sized avatar
๐ŸŽฏ
Focusing
๐ŸŽฏ
Focusing

Block or report MONA100421

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
MONA100421/README.md

Hey ๐Ÿ‘‹, I'm Chenyi Weng (็ฟ็”„ๅฎœ)

A Software Engineer & Data Scientist in the making ๐ŸŒŸ
Bridging business insight with scalable software and machine learning solutions.


๐Ÿš€ About Me

  • ๐ŸŽ“ Master's student in Spatial Data Science @ USC (STEM, Class of 2025)
  • ๐Ÿ’ป Experienced in building machine learning pipelines, scalable data systems, and web applications
  • ๐ŸŒ Based in Los Angeles, originally from ๐Ÿ‡น๐Ÿ‡ผ Taiwan
  • ๐Ÿ”Ž Passionate about AI, cloud platforms, and full-stack engineering
  • ๐Ÿ“ฌ Portfolio: mona100421.github.io/chenyi/
  • ๐Ÿ’ผ Connect: LinkedIn

๐Ÿง  My Journey

I started with a business and information management background in Taiwan ๐Ÿ‡น๐Ÿ‡ผ,
which gave me strong foundations in strategy and data thinking.

Now at USC, I am transforming into a software engineer and machine learning practitioner,
crafting solutions that scale from big data pipelines to deep learning models.

I believe in combining business sense + technical execution to create real-world impact.


๐Ÿ“Œ Featured Projects

Project Tech Highlights
Machine Learning Frameworks (DSCI552) Python, scikit-learn, TensorFlow Built classical & deep learning models (LogReg, RF, SVM, CNNs). Designed active learning SVMs and multi-label pipelines, achieving >95% accuracy.
Audio/Image Classification Pipeline CNN, Keras End-to-end ML pipeline from preprocessing to model tuning; evaluated with ROC AUC & F1, reproducible GitHub repo.
Scalable Data Extraction (DSCI550) Python, Spark Extracted & transformed million-scale unstructured datasets with regex + batch jobs, achieving >90% clean data accuracy.
Interactive Dashboards (DSCI550) Plotly, Dash Built data visualization platform with drill-down analytics to support decision-making.

โžก๏ธ More projects on my GitHub


๐Ÿ› ๏ธ Tech Toolbox

Python TensorFlow Keras scikit-learn Pandas React Node.js FastAPI PostgreSQL AWS Docker


๐Ÿ† Highlights

  • ๐Ÿงฉ Multilingual: Mandarin (native), English (fluent)
  • ๐Ÿ“Š Cross-disciplinary: Business + Data + Engineering
  • ๐ŸŒฑ Always learning: from scalable infra to applied ML
  • ๐Ÿ’ก Goal: Become a Software Engineer / ML Engineer who bridges data science and engineering at scale

๐Ÿ“ฌ Reach Out

I'm open to software engineering, data engineering, and applied ML opportunities.
If you're building AI-driven products or scalable systems, I'd love to collaborate!

๐Ÿ“ง wengchen@usc.edu
๐ŸŒ Portfolio
๐Ÿ”— LinkedIn

Pinned Loading

  1. chenyi chenyi Public

    HTML 1

  2. Chen_Yi_Weng_MT1_DSCI_552 Chen_Yi_Weng_MT1_DSCI_552 Public

    Jupyter Notebook

  3. data-structures-algorithms-coursera data-structures-algorithms-coursera Public

    Java

  4. DSCI552_Multi-Label-Classification-on-Anuran-Calls DSCI552_Multi-Label-Classification-on-Anuran-Calls Public

    Forked from USC-DSCI-552/homework-7-MONA100421

    homework-7-MONA100421 created by GitHub Classroom

    Jupyter Notebook

  5. DSCI552_Regression-Modeling-and-KNN-Analysis DSCI552_Regression-Modeling-and-KNN-Analysis Public

    Forked from USC-DSCI-552/homework-2-MONA100421

    homework-2-MONA100421 created by GitHub Classroom

    Jupyter Notebook

  6. DSCI552_Supervised-Semi-Supervised-Active-Learning DSCI552_Supervised-Semi-Supervised-Active-Learning Public

    Forked from USC-DSCI-552/homework-8-MONA100421

    homework-8-MONA100421 created by GitHub Classroom

    Jupyter Notebook