Post Job Free

Resume

Sign in

Data Analyst

Location:
Berkeley, CA
Posted:
April 30, 2016

Contact this candidate

Resume:

**** ********** ***, ********, **, ***** 310-***-**** acukv3@r.postjobfree.com

Objective: Data Analyst or Similar Quantitative

Education:

University of California, Berkeley Expected graduation: May 2016 Master of Arts in Statistics

! Topics included: machine learning, statistical computing through R and Python, big-data analysis, data mining, numerical analysis, optimization.

University of California, Los Angeles Sept. 2012 – June 2015 Bachelor of Science in Applied Mathematics; Bachelor of Science in Statistics

! Magna Cum Laude, GPA: 3.85

! - Major GPA in Applied Mathematics: 3.866 - Major GPA in Statistics: 3.931 Skills:

! Proficient in R Studio, Python, SQL, SAS, SPSS, STATA, C++, Matlab, Bash, Unix, Git, Latex, Microsoft Word, Excel and PowerPoint

Experience:

Department of Statistics, UC Berkeley Berkeley, CA Graduate Student Instructor for STAT133: Concepts in Computing with Data Jan. 2016 – Present

! Give a weekly lab lecture on data wrangling, data visualization and R programming to explain how to analyze real-life data

! Hold weekly office hours to help students solve problems and projects

! Work in a team of five GSIs and provide suggestions and feedback to the content or assignment for the professor Department of Statistics, UC Berkeley Berkeley, CA Statistical Consultant Sept. 2015 – Dec. 2015

! Provided statistical consulting services for campus researchers from different subjects, such as biology, psychology, economics and sociology

! Gave advice on experimental design, modeling methods and power testing

! Provided follow-up sessions to review the analysis and interpretation Johnson & Johnson Medical Ltd Suzhou, China

Finance Intern July 2015 – Aug. 2015

! Managed and updated accounts payable/receivable in Excel and a SAS database for Johnson and Johnson medial devices

(valued at 10k – 500k per device)

! Accounting and database management led to more efficient discovery of unpaid invoices and accounting errors University of California, Los Angeles Los Angeles, CA Reader Sept. 2013 – Jan. 2014

! Graded math homework/quizzes, and recorded scores

! Summarized the major mistakes students made in their homework and quizzes, investigated if there were some misunderstandings and reported them to the professor and teaching assistants Projects:

[Python] Machine Learning Project: High-frequency Stock Trading Data, UC Berkeley Spring 2016

! Created feature sets, determined prediction time stamps and labeled mid-price movement and bid-ask spread cross using the Limit Order Book of AAPL dataset for transaction happened at the nanosecond scale. Trained models using SVM, Random Forest and Gradient Boosting and utilized cross validation to tune parameters. Modified and implemented trading strategies based on machine learning predictions and calculated profits.

[Python, R] Twitter API data text mining, UC Berkeley Spring 2016

! Extracted Twitter API data about Grammy Award using python. Worked in a team of six to conduct analyses on nominees' timelines to analyze their tweeting preferences and social networks. Compared the API data with Google search index to analyze the popularity. Visualized the findings using ggplot2 package in R and gave a poster presentation.

[Python] Loss Aversion in Decision-Making under Risk, UC Berkeley Fall 2015

! Investigated and provided evidence for phenomenon where individuals’ gambling decisions are influenced more by the amount of potential loss than by the amount of potential gain. Cleaned and worked on both the brain image data set and the gambling behavior data using python. Did regression, PCA and heat maps to highlight the relative brain regions that were sensitive to the gain and loss.

[Spark, SQL, R, AWS] Big Data Analysis using parallel computing, UC Berkeley Fall 2015

! Created an SQLite database for 12GB airline data from 1987 to 2008 through Amazon EC2 instance. Created tables for each individual year to reduce the memory use. Utilized Spark with 12 slave nodes to perform efficient analysis on the database and found out the delay patterns of flights.



Contact this candidate