SQL, Python, Java, Tableau, data analysis, machine learning

EDUCATION

Columbia l i University i i - M.S. Applied Analytics - New York, US 2019.09 - 2020.12

Related Courses: Statistics, Algorithm and Data Structure, Object Oriented Design, Machine Learning, Managing Database Southwest Jiaotong i University i i - B.A. German Language and Literature - Chengdu, China 2014.09 - 2018.06 GPA: 3.7/4.0(top 2%) Awards: First And Second Prize Scholarships for 8 consecutive semesters COMPETENCIES

Programming i Languages/ Tools: l Java, Python, JavaScript, SQL, MySQL, MongoDB, Spark, Tableau, Google Analytics INTERNSHIPS

Webomates(Information i Technology) l - Data Scientist Intern - New York, US 2020.05 - 2020.08 Examine and improve Amazon MTurk Crowdsource automation accuracy Retrieved and performed data analysis on 10 million data points from database using SQL and PySpark Predicted automation result accuracy using Logistic Regression under different sampling methods, obtained 90% accuracy Utilized AI model(l LSTM) to uncover relationships between failure reasons with other features, involving NLP techniques like Tokenization, Stemming, Word Embedding, i improved system accuracy by 10% Colgate-l Palmolive l li - Business Analyst Intern - Guangzhou, China 2018.10 - 2019.12 Conducted sales analysis using Excell, built dashboards with Tableau l, and delivered presentations for business audience Collaborated with cross-functional teammates to produce strategy report including competitive i i product analysis, l i product positioning i i i for a new type of toothpaste marketing Managed in tracking metrics like sales, gross profit, inventory turnover and communicating with all distributors in Canton region PROJECT EXPERIENCE

JOBplus: l A Personalized li Job Recommendation i Engine i (http://3.134.112.194/j jupiter/i ) Designed and implemented an interactive web page(HTML, CSS, JavaScript i ) for users to search positions and apply Revised personalized recommendation based on collected search history and favorite records Created Java servlets with RESTful l APIs to handle HTTP requests and responses Used MySQL to store real position data(company, requirements, deadline, etc.) and deployed it to Amazon RDS WiDS(i Woman i in Data Science) i Datathon 2020(Python) Reduced MIT's GOSSIS dataset dimension from 188 columns to (144, 130,000) based on exploratory analysis as well as complex context

Used Adversarial i l Validation li i to assure same distribution happening in train and test data Applied LR, RF, XGBoost, KNN, MLP models on both One-Model and Many-Model approaches to gaurantee testing accuracy, both approaches achieved ca. 92% percision rate

New York Airbnb i House Price i Projection(j i R)

To predict house price of Airbnb in NY and provide recommendations for house owner as well as house tenants Conducted data preprocessing and filtered useful features by correlation matrix and using LASSO model Tested multiple models e.g. Logistic i i Regression, i Random Forest and performed k-fold l cross-validation li i to explain relationships between house price with surroundings, customer feedback, ratings etc. Generated data visualizations to present the final result and acquired an A from professor Weiyi Zhong

212-***-**** 丨wz2513@columbia.edu

linkedin.com/in/weiyizhongiris 丨github.com/weiyizhong95

Contact this candidate