Data Analysis

Fan Wu

**** ***

Street, Davis, CA, *****

acvq8m@r.postjobfree.com ò 530-***-**** ò https://www.linkedin.com/in/fanwu212 Statistics Master with extensive experiences in quantitative research and statistical data analysis utilizing computer database and programming software. Additional qualifications are:

§ Proficient with MS Office, Excel, R, SQL

§ Experience with Python

§ SAS Certified Base Programmer for SAS 9

§ Self-Starter and Quick-Learner

§ Statistical Modeling Experience

§ Never-end Passion in Large Datasets

EDUCATION

Master of Science in Statistics, University of California Davis (GPA 3.63/4.0) Dec 2015 Relevant Coursework: Statistical Methods for Researches, Machine Learning, Categorical/Multivariate Data Analysis, Python for Data Mining, Mathematical Statistics Bachelor of Science/Arts in Mathematics/Economics, University of Colorado Denver (GPA 3.79/4) May 2014 Bachelor of Arts in Economics, China Agricultural University (GPA 3.74/4) May 2011 PROJECTS

MACHINE LEARNING: Crime Rate in a Neighborhood Mar 2015-May 2015

§ Unsupervised Learning: Conducted MDS and K-means to identify pattern of crime rate. Determined high- rate neighborhood may have great effect

§ Supervised Learning: Used 6 models (Logistic Regression, SVM, LDA, KNN, Regression Trees, Random Forest) and reached lowest MCR (0.25) with SVM BIG DATA: New York Taxi Data Analysis Mar 2015-May 2015

§ Processed and merged 2 separate 50-Gigabyte CVS data both in R and Shell and developed EDA

§ Fitted regression for conducting advance analysis to statistically test significant factors related to taxi fare

§ Improved efficiency by parallel processing with 5 times quicker for Shell and 2 times for R PREDICTIVE MODEL: Car Data Analysis Jan 2015-Mar 2015

§ Visualized data to initially explore variables relationship

§ Conducted multicolinearity check and stepwise model selection using BIC

§ Built a multiple linear regression with cross validation on mileage per gallon and other car features and ran diagnostics

UNSTRUCTURED DATA: Text Process and Email Classification Oct 2014-Dec 2014

§ Created an email filter on the MAC platform using R

§ Processed, compiled and extracted text for approximately 6500 emails via regular expressions

§ Detected and evaluated variables 20 out of 30 to separate HAM and SPAM by data visualization

§ Classified raw e-mails utilizing KNN and Classification Trees with 87% classification rate EXPERIENCES

Statistical Bureau, Wenzhou, China Jul 2015-Aug 2015 Data Analytics Intern

§ Worked with analysis team to detect the pattern of business opening and population trend

§ Compiled, integrated and managed data via EXCEL with PIVOT TABLE, VLOOKUP

§ Performed EDA and data visualization to create 2014 annual reporting book University of Colorado, Denver, CO Jun 2013-Aug 2013 Research Assistant

§ Assisted Professor Daniel Rees in researching the topic Deployments, Combat Exposure and Crime

§ Explored history of 4 US Army brigades based in Fort Carson, CO with strict attention to detail

§ Collected, arranged scattered data from newspapers and blogs, ensuring accurate statistics

§ Created a definite and concise data set of 4 brigades

Contact this candidate