• Perform analysis of large volume of POS, web, email, customer and other quantitative data sets• Create testing and learning analytic methods and develop consistent process of analysis• Prove and disprove business hypothesis through data and statistical analysis• Use strong analytical skills to provide insights as well as recommendations for changes and convince key leadership of testing benefits• Apply retail business and key KPIs for success in driving Members engagement and conversion in store and online• Support report automation projects, build relationship between channel owner and automation team, coordinate data validation progress with centralized data warehouse and vendors.• Analyze and segment members based on RFM model, PCA and K-means models• Work with other analysts to understand multi-channel performance and support member engagement optimization• Using R and Python to build predictive models like Random Forest, Logistic Regression, SVM and Multinomial Logistic Regression to better understand member behaviors and business trend and design personalization tests cross mobile channels

• Generated Salesforce report and analyzed participant profile for 43 programs and provided targeting strategy• Performed competitor analysis (SEO) of new program offering, online & partnership programs and visualized pricing trends from 2015 to 2017• Used R and SQL to merge and analyze international participation data and presented to management team with actionable insights and recommendations

• Developed Python code to scrape demographic information from third-party data for 170K websites• Created customized SQL queries to select and merge browsing, clicking and conversion histories for 400 MM users• Built 3-hidden-layers neural networking and random forest models with R, identified significant predictors of conversion• Launched Facebook campaigns for gender-skewed clients to test prediction accuracy (85%)• Launched A/B testing for re-targeting campaigns to compare conversion lift (50%) with benchmark • Presented to C-suite, marketing team and tech team with implementation plan of machine learning optimization

Supervised by Prof. Silvia Knobloch-Westerwick, I worked at the entertainment lab as an undergraduate research assistant for 10 hours per week. I created stimuli for Online vs. Offline Selective Exposure study including news leads and magazine articles. I run lab sessions for two semesters (10 hours per week). And I also analyzed data and content from the experiment, using SPSS to run F test.