Data Analyst

EDUCATION

Columbia University **/**** - **/****

MA in Statistics GPA: 3.33

Relevant courses: Advanced Data Analysis, Applied Data Science, Data Mining, Machine Learning, Probability Theory. University of Illinois at Urbana-Champaign 08/2014 - 05/2018 BA in Economics and Psychology GPA: 3.68

Relevant courses: Econometrics, Industrial and Organizational Psychology, Linear Regression, Survival Analysis. YUGUANG (MICHAEL) LYU

******@********.*** 347-***-**** Yuguang Lyu 411 W 35th St, New York SKILLS

Data management software: Excel, R studio, SQL Server Management Studio, SPSS, Stata, Tableau, WordPress. Programming Language: HTML, Java, Python, R, SQL.

Python Libraries: Keras, Matplotlib, Numpy, Pandas, Pillow, Plotly, Scikit-learn, SciPy, Scrapy, TensorFlow, XGBoost. Language: Cantonese (Fluent), French (Intermediate), Mandarin (Native). WORK EXPERIENCE

E-Commerce Data Analyst Intern, Tianxingyun Supply Chain Co., Ltd., Shenzhen, China. 06/2019 - 08/2019 Established ETL pipeline to automate repetitive data manipulation and saved company 8 hours of working time daily. Communicated with cross-functional partners in product management to understand business logic. Designed data schema and centralized joining of 30 tables in SQL Server Management Studio to accommodate sales data reporting.

Used Python (selenium webdriver) to build a web scraping bot that solves CAPTCHA and extracts sales data

(~1.2 GB) from 50+ data sources. Exported the data into SQL Server Management Studio. Drafted templates of reusable SQL queries that analyze month-to-date gross margins of cross-border trading. Visualized (Plotly) sales data and scheduled weekly reports to sales department partners. Web Content Developer, Shanghai Yunqiao Advertising Co., Ltd., Shanghai, China. 05/2018 - 08/2018 Optimized company strategy for our client (Oanda Corporation) to achieve 100+ new Forex treading platform subscribers per month.

Communicated with our client through emails and learned their business initiatives in financial market. Managed our client’s social media and helped our client to acquire 200+ new Facebook page followers in 3 weeks. Used WordPress to build an online Forex wiki (400+ interconnected terms) for our client’s website. Created HTML pages for our client’s Forex analytical articles using WordPress. PROJECTS

Santander Bank Product Recommendation Analysis 09/2019 - 10/2019 Led a team of 12 to create a recommendation system for bank products including mortgage and credit card. Performed EDA on Santander Bank’s 18 months of customers behavior data (~2.4 GBs) by using Tableau to visualize customer patterns (Gender, Age, Employment Status, etc.) on different bank products. Conducted missing value analysis and filled in 25043 missing values with their best estimates. Performed feature engineering to transform 51 variables to 122 and aggregated each customer’s multiple records. Used Python to build a XGBoost model that predicts which products customers are likely to purchase and achieved an average accuracy rate of 88.2% for top 7 most purchased products. Chicago Crime Data Analysis 02/2019 - 03/2019

Analyzed Chicago Police Department’s 2018-2019 crime data (~200 MBs) and predicted future crimes. Performed EDA using MLR and found the most influential factor to total crime occurrence: income per capita. Applied K-means clustering to find 30 centroids of violent crimes (burglaries, murder, rape, etc.). Enabled interactive visualization of these 30 centroids on Chicago’s map using Google API. Predicted future violent crime occurrences at these centroids the by applying LSTM algorithm. Analyzed prediction results and suggested future locations for police stations. Prepared PowerPoint and presented of our project to 30+ audience.

Contact this candidate