Xingyin(Rosy) Xu


my pic

Hi there!

I am a Master's student in Data Science at New York University. I received my Bachelor's degree at University of California, San Diego with a major in Probability and Statistics and minors in Data Science and Economics.
This semester, I'm thrilled to dive into Big Data, Machine Learning, and Visualization in Machine Learning. My passion lies in Data Analysis, Data Visualization, and Machine Learning, and I can't wait to explore these subjects further.


Projects


movie rating
MOT16 - Visual Tracker

Model visualization tool for developers working on Multiple Object Tracking (MOT) models

Computer Vision Model Visualization MOT
Report Github Repo
movie rating
Spotify Popularity Analysis

Explored relationship between song features and song popularity in Spotify using Machine Learning and Deep Learning

Python Mann-Whitney U Test Linear Regression SVM Collaborative Filtering Model
Report Github Repo
heart disease
Mitigating Overconfidence Bias in Large Language Models (LLM) through Knowledge Transfer

Utilized Chain of Thought (CoT) from GPT and transffered knowledge to smaller LLMs by fine-tuning

Pytorch LLM Vicuna CoT Verbalized Confidence
Paper Github Repo
heart disease
Data Related Job Salary Analysis

Data Visualization on relationship between data related job salary and employee's personal information

Matplotlib Pandas Numpy Sklearn LGBMRegressor Regression Tree
Report Github Repo
heart disease
Movie Ratings Analysis

Investigated movie ratings with Statistical Testings and Machine Learning Models using Python

Mann-Whitney U Test KS Test Regression Models Regularization Cross Validation ROC AUC Curve
Report (Statistical Tests) Report (ML) Github Repo
Rating Prediction
Rating Prediction with Collaborative Filtering

Clothes rating prediction using Jaccard Similarity in Python

Text Analysis Feature Engineering Cold Start Jaccard Similarity Regularization Latent Factor Model
Report GitHub Repo
heart disease
Heart Disease Prediction from Health Indicators

Heart disease prediction using Supervised Machine Learning Models

Logistic Regression Decision Tree SVM KNN ROC AUC Curve Cross Validation
Report Github Repo
Rating Prediction
Social Media Influencers' Advertisement in Social Networks and Effect on B2C store in China

Applied SIS Model in epidemiology to simulate the cloth sales under the effect of social media influencers' advertisement

SIR Model Python Social Media Parameter Simulation
Report GitHub Repo

Skills and Tools

python sql excel java sql html tableau

pandas numpy matplot sklean seaborn mongodb