Portfolio
AI Agent Application
AI-Powered Resume Optimization Tool
- An intelligent AI Agent application that analyzes job descriptions and resumes, identifies skill and experience gaps, generates content optimization plans, and rewrites resumes. Built with CrewAI, DeepSeek LLM, Pydantic, and Gradio for an end-to-end, interactive workflow with data-driven insights and visualized match scores.
Data App
Insights & Analysis - My Stocks Portfolio
- Models to visualize chosen company’s operating condition and market power.
Warren Buffett U.S. Stocks Portfolio
- A simple data App created with streamlit to investigate the stocks held by Warren Buffet.
Data Science Projects
Humana-Mays Healthcare Analytics
- The purpose of this project is to identify patients likely to overuse opioids by using machine learning tools.
Detect Non-negative Tweets Towards Airlines
- A Sentiment analysis using tf-idf vectorizer and MultinomialNB Classifier.
Food Trend Detection by Co-occurence Matrix
- The purpose of this project is to help retailers see the rise and fall of certain categories of food before competitors do.
- EDA for the trending youtube videos US dataset. Performed some NLP technique to deeply explore the contents of youtube videos, and showed some personal opinions.
- The project is to distinguish images of dogs from cats based on the form of VGG16 architecture.
RNN for Sentiment Classification 
- The project is to predict which Tweets are about real disasters and which ones are not using recurrent neural network.
- The purpose of this project is to predict the final price of each home with 79 explanatory variables describing almost every aspect of residential homes in Ames, Iowa.
Google Play Rating Exploratory Data Analysis 
- The purpose of this project is find out what kind of Andriod Apps are most likely to get high ratings in Google Play Store.
Business Analytics Projects
National Chain Retailer Attraction Plan(Team Project)
- The project objective is to attract a national retailer and identify an optimal location for it in downtown Rochester with consideration of economic status, demographic attributes and business opportunities. The ultimate goal is to improve residents’ quality of life and increase the city’s employment opportunities, sales tax revenue, building occupancy, and retail offerings.
Next Yogurt Flavors to Launch(Team Project)
- The goal of this project is to provide analytics to help determine what the next flavors to launch should be. We used store sales data to find out the most popular existing greek yogurt and regular yogurt flavors, and then conducted a Turf analysis based on the survey data to provide recommendations for the new flavors.
Find The Best Product Line Scenario(Team Project)
- The goal is to make recommendations about the toy horse product line. We first used regression to estimate the conjoint model at the individual level, and then explored the best market segmentations by conducting post-hoc clustering and priori segmentation analysis. Lastly, we simulated market shares for different product-line scenarios and identified the best possible product line strategy given considerations related to competitive response, cannibalization, profitability and long-run performance.
- The general goal of this task is to distinguish potential high-value consumers and separate them from low-value consumers.
- The goal of this project is to code up a simple system that reads and processes crime record data in the Baltimore Police Department, and visualizes crime location patterns depending on userspecified conditions.
- This project is to detect what factors are likely to trigger more 911 calls.
