John Van

Hey! I’m John

I'm currently a Data Scientist at CVS Health, working within the Aetna Clinical Analytics team. I specialize in building predictive models, performing statistical analysis, and leveraging data to solve real-world business problems.

Outside of work, I love to workout, spend time with my dog, play piano, and test my joints on the basketball court. Feel free to reach out to me on LinkedIn or email me at johnvan1999@gmail.com.

UC Berkeley, Master of Information and Data Science '24
UC Berkeley Data Science, B.A. '21
UC Berkeley Economics, B.A. '21

Projects

DeeBoT (Berkeley DBT)

An innovative AI chatbot built on top of OpenAI's GPT-4 architecture that incorporates the fundamental skills of dialectical behavior therapy (DBT). Designed to serve as a personal DBT therapist, DeeBoT delivers customized guidance tailored by individual stories and emotions, fostering a more personalized and deep therapy experience.

This project aims to demonstrate how new developments in NLP can be utilized in mental health education, particularly in making DBT more accessible. It aims to contribute to the field of mental health services, offering practical solutions that enhance user experience and accessibility.

LLM NLP

Link to Project

Fraudulent Job Postings (NLP)

Built a fake job posting detector using a suite of natural language processing techniques to identify fraudulent listings and protect job seekers.

The project compares four approaches—TF-IDF with classical machine learning models, GloVe embeddings, Bag of Words,and BERT—to understand trade-offs in interpretability, performance, and compute cost for real-world deployment.

NLP Machine Learning

Link to Code