YI ZHANG

adkey6@r.postjobfree.com · 646-***-**** · Seattle · Yi Zhang Yi_Zhang

Education

Columbia University New York, NY

• M.S. in Applied Analytics (STEM) (GPA: 3.92/4.00) Dec. 2020

• Relevant Coursework: Managing Data, Python for Data Analysis, Anomaly Detection, Machine Learning Lancaster University United Kingdom, UK

• M.S. in Strategic Management (GPA: 3.77/4.00) Oct. 2014 Zhejiang Gongshang University China, CN

• B.A. in Financial Journalism (GPA: 3.67/4.00) Jun. 2013

Working Experience

Data Analyst Intern New York, NY

Columbia University Marketing Department Nov. 2019 - Dec.2020

• Innovated interactive year-end reports and shaped unstructured data into 10+ dashboards by Tableau in FY20

• Created weekly pipeline reports by Google Analytics and Google Data Studio for web advertising and email team

• Established funnel models and key metrics by SQL to monitor campaigns which facilitated data-driven decision-making

• Optimized user experience and reduced expenses on candidate screening by designing an A/B test that discovered crucial effect of the length of request form on user registration rate Business Analyst Manager Singapore, SG

Healy Consultants Group PLC Apr. 2015 - Jul. 2018

• Fulfilled 20+ corporate clients’ business expansion goals in 10+ countries by conducting macro and micro marketing research, providing feasible strategy proposals and preparing customized business plans of clients’ target markets

• Increased sales amount to US500k in 2016 and US600k in 2017 as a project owner and won honor of 2016 best employee

• Actively participated in designing Healy Consultants’ Chinese marketing strategy and proposed Chinese SEO strategy

• Prompted MySQL for the internal database management and designed the schema of business consulting department

• Led a team of 2 full-time analysts and 1 intern to efficiently complete 5+ international projects

Project Experience

Capstone Project: Predictive Index Analysis Aug. 2020 - Dec.2020

• Led a team of 9 members to assist a human resources consulting firm, MindWire, in conducting a research of client health

• Analyzed the user activities of clients on Predictive Index and discovered key indicators of client retention

• Designed a customized dashboard to monitor client health and facilitate data-driven decision making

• Composed a detailed user manual including key metrics definitions, dashboard introductions and specific use cases Predict Mortgage Default Rate with AutoML Jul. 2020 - Aug. 2020

• Explored 80,000 anonymous mortgage data with 90 dimensions by Python (Numpy, Pandas, Seaborn and Matplotlib)

• Conducted feature engineeringwithWeightofEvidence(WOE) and SyntheticMinorityOversamplingTechnique(SMOTE)

• Performed model construction, model testing and evaluated models by ROC, Precision-Recall and the Cumulative Lift

• Used AutoML (h2o) for model construction and ranked top 3% over 300 participants (leader-board ranked by ROC) Predict Rental Prices with XGBoost Oct. 2019 - Dec. 2019

• Cleaned, processed, and analyzed 36,839 properties in New York listed on Airbnb with tidyverse, ggplot2 and mice

• Manipulated and selected 13 features out of 91 variables by Lasso and utilized XGBoost to predict the rental prices

• Visualized comparisons between predicted and actual fares based on location, date and time with ggplot2 of R and Tableau

• Predicted test data of 9210 New York Airbnb properties with unknown rental prices and ranked top 3% in Kaggle

Skills

• Languages/Frameworks: Python, PySpark, SQL, R, Machine Learning, A/B Testing, Anomaly Detection, NLP

• DBMS/Techniques: MySQL, Jupyter Notebook, Databricks, Teradata, Tableau, AWS, Google Analytics & Data Studio

Contact this candidate