-
🔭 I’m currently work at FounderWay as an AI Engineer, and I'm also working on building a stock trading bot and developing HelpBuddy, a startup that assists people undergoing eviction by providing social service recommendations and legal support resources.
-
🌱 I’m currently learning about reinforcement learning and Markov decision processes.
-
🤔 I’m looking for full-time jobs in roles like AI Engineer, Front-End, Full-Stack Developer, Data Scientist or Machine Learning Engineer.
-
📫 How to reach me: chloeyankr@gmail.com
-
💻 LinkedIn: https://www.linkedin.com/in/chloe-yan1
-
📜 View my Resume
-
⚡ Fun fact: I’m passionate about tech in communication and humanities, and I have a pet rabbit named Luna!
-
Machine-Learning-for-Surface-Coating-Optimization : Used R and ML skills like classification, regression and optimization to train models to predict surface corrosion speeds.
-
Stack Overflow-Inspired Web Application: This project implements a full-stack webapp with functionality inspired by Stack Overflow, supported by industry standards in software design, modularization, end-to-end testing and a CI pipeline.
-
Fake News Lab: Analyzing Covid-19 News: This project analyzes the most discussed topics and keywords surrounding Covid-19 news using ML techniques. We employed Latent Dirichlet Allocation (LDA) and text summarization methods to extract key insights from a dataset of Covid-19 related discussions.
-
Graphical Image Manipulation and Enhancement: Designed a view for an image processing application, featuring a graphical user interface which allows a user to interactively load, process, and save images. Uses Java Swing to build the GUI.
-
Formula-One-F1-Database-Management-System: Created a relational SQL database that captures and organizess data related to Formula One racing. The database stores information and offers users the ability to query and analyze various aspects of the sport in the Python application.
-
Credit Card Fraud Detection Using Clustering and Classification Models: This project explores factors that differentiate between fraudulent and non-fraudulent transactions with ML techniques. By applying clustering and classification models, ensemble learning, and feature engineering, we identified key patterns and variables that are most indicative of fraudulent behavior.

