Xi Yang

adjm23@r.postjobfree.com +86-187******** Shanghai

EDUCATION

New York University New York, NY

M.S. in Data Science (4.0/4.0) May 2022

Relevant Courses: Machine Learning, Big Data, Probability and Statistics for Data Science,Database System University of Pittsburgh Pittsburgh, PA

B.S. in Industrial Engineering (3.98/4.0) Sept. 2016 - May 2020 Minor: Math, Economics

SKILLS

l Languages: Python (>100,000), SQL (>100,000 lines), R, MATLAB, Access l ML Algorithms: Linear Regression, Random Forest, Logistic Regression, Naïve Bayes, Decision Tree, KNN, SVM, XGboosting, LightGBM, K-Means

l Data Visualization: Tableau, Matplotlib, Seaborn, ggplot l Statistic: predictive modeling, hypothesis testing, AB test PROFESSIONAL EXPERIENCE

Jones Lang LaSalle Sichuan, China

Data Cleaning intern - Valuation Advisory Service Team Jun. 2020 - Aug. 2020 l Assisted in the preparation of commercial property valuations including data cleaning and data analysis l Conducted an analysis regarding the distribution of logistics and warehouse in the future based on the data of logistics and warehouse collected from the database of Chengdu Municipal Bureau of Planning and Natural Resources using SQL l Maintained and updated the internal database of 100,000+ data using SQL Commercial Aircraft Corporation of China Shanghai, China Data Analyst intern - Strategic Planning Department Apr. 2020 - Jun. 2020 l Build a Web Scraper with python to scrap flight test news from various news websites l Generated 20+ pages reports in a weekly basis and published on company internal website based on the data collection l Analyzed and evaluated reports by comparing the flight tests result across the world PROJECT EXPERIENCE

Regression Supervised Learning Project Sept. 2020 - Dec. 2020 l Scrapped the data of 200+ famous food vloggers’ videos (i.e. the hits, comments and labels of videos, the information of vloggers) from a Chinese leading video website (Bilibili), cleaned the data and implemented feature engineering to create more features

l Built different regression models (linear regression, KNN, DT, XGboosting, LightGBM, Random Forest) and compared the result of models, finding LightGBM model achieving 30% higher prediction in terms of MSE than the baseline result l Helped advertisers to evaluate the future video plays of their targeted KOL vloggers and helped individual vloggers create popular videos according to the SHAP result (shows how features impact target variable) Yelp Data Analysis Project Sept. 2020 - Dec. 2020

l Implemented data visualization of various features that contribute to yelp review stars using Python and Tableau l Generated word cloud of customers’ reviews for both high review stars and low review stars restaurants to find high frequency words in reviews

l Conducted a sentiment analysis on customers’ reviews and helped restaurants’ owners better understand customers’ reviews Created a Database for the Allegheny Health Network (AHN) Center for Inclusion Health (CIH) Feb. 2019 - May 2019 l Built a database using Access to save the information of underserved immigrant pregnant women l Implemented the function of database in summarizing all variables and determining various linkages in the data collected, helped Immigrant Health Program in providing emotional support for women throughout pregnancy and following birth Created Simulation Models for Ainan Company (Japan) Sept. 2019 - Dec. 2019 l Built simulation models using R to simulate the survival rate and egg laying rate of each coop based on the data l Generated the distribution of number of chickens in each coop per week and made suggestion to the company in maximizing profit, getting 10% increase in total profit