BOYING XU
**** ********* ******* ****, ********, NJ, 07094 201-***-****, ****@*******.***, https://www.linkedin.com/in/xuboyingmailto:********@***.***
PROFESSIONAL SUMMARY
A self-motivated, persistent, results-oriented data fanatic with extensive experience and measurable achievements in data analytics and risk management seeking for a full-time job in data science filed.
SKILLS
Python, R, SQL, Tableau, SAS Certified Advanced Programmer for SAS 9, SAS/EG, SAS/EM, SAS/OR, Spark, Hadoop, Pig, Hive, MapReduce, Microsoft Excel
EMPLOYMENT
Davidson Laboratory Hoboken, NJ
Data Analyst Intern 6/2015-8/2015
Collected historical water data from dozens of water stations along Hudson River; leveraged clustering and time-series forecasting techniques to build models for water level prediction.
China Customs Xiamen, China
Analytics Specialist 1/2013-7/2014
Detected dozens of frauds and retrieved more than 5 million dollars of tax losses.
Managed a team to oversee the operation of multiple departments; identified their vulnerabilities in management, delivering advanced analytics to improve their performance and establish better strategies.
Senior Data Analyst 8/2005-1/2013
Initiated projects to optimize and update the functions of Enforcement Assessment System.
Manipulated large data sets with SQL and SAS; applied statistical models and data mining techniques to drive decisions and generate actionable insights.
Designed and computed a set of statistical indicators to access the performance of customs operation across the country.
EDUCATION
Stevens Institute of Technology Hoboken, NJ Master of Science in Business Intelligence and Analytics 8/2014-12/2015
Shanghai University of Finance and Economics Shanghai, China Bachelor of Science in Mathematical Statistics 9/2001-6/2005
COURSEWORK
Statistics, Experimental Design, Machine Learning, Data Mining, Big Data, Optimization, Web Analytics, Social Network Analysis, Data Warehousing, Text Mining, Data Visualization
ACADEMIC PROJECTS
Stevens Institute of Technology
Digit Recognizer Used Python to build a number of classification models, such as Random Forest, Naïve Bayes, Logistic Regression and KNN to identify a hand written single digit; evaluated them with ROC curve and accuracy score; ran the selected model on Spark MLlib and Azure to compare the efficiency; adopted PCA, SVD, LDA and Univariate Feature Selection to do dimension reduction, and compared their effects in terms of model performance and runtime.
TalkingData Mobile User Analysis Given mobile data in China, used R to visualize the usage density and geolocation; predicted users' demographic characteristics based on their behaviors and mobile device properties.
Box Office Prediction Used Python to scrape IMDB and gathered movie data; preprocessed and transformed the data, and employed various regression algorithms, such as SVR, Random Forest, and Linear Regression to forecast the box office of a new movie.