🎓 Data Theory @ UCLA | 🤖 Machine Learning Developer | 🧠 AI Researcher | 🌐 Full-Stack Engineer
📍 San Diego → Los Angeles | 📬 derekshi@ucla.edu | LinkedIn
I'm a data scientist and builder passionate about using AI to solve real-world problems.
Currently leading UCLA's largest data science club and building scalable, AI-powered tools for education and community.
- 🧠 AI/ML Intern at Think Data Education – designing curriculum-based AI chatbots deployed on AWS
- 📚 Founder of Booked – full-stack web app and ML-powered recommendation engine to foster youth reading
- 🤖 President of UCLA DataRes – building an LLM chatbot that generates course plans using LangChain + Pinecone
- 📈 Project Director at National Data Science Corps – led a CNN project on American Sign Language recognition
Languages: Python, Java, C++, SQL, JavaScript, R
Libraries & Frameworks: TensorFlow, Keras, PyTorch, LangChain, Scikit-learn, XGBoost, Pandas, NumPy, Flask
Full-Stack: Express.js, HTML5/CSS, MongoDB Atlas, AWS
Tools: Git, VSCode, Pinecone, Gemini, Google Cloud, Slack, GitHub Projects
🔹 Booked
A cloud-based community site that uses collaborative filtering + SVD for personalized book recommendations.
Full-stack: MongoDB, Express, JS, HTML/CSS. Managing a team of 15 interns.
Utilizes UCLA Dev API, LangChain, and vector search to help students create optimized course plans.
Trained a convolutional neural network on 24 ASL letters using TensorFlow and image classification.
XGBoost regression with hyperparameter tuning and PCA to optimize housing price predictions.
Feel free to reach out if you want to chat about AI, data science, or collaborate on projects!
📫 Email: derekscreek@gmail.com
🔗 LinkedIn: linkedin.com/in/derek-shi-6331672aa
💻 GitHub: github.com/derekshi1