Data Analyst

217-***-****

San Jose, CA, *****

*************@*****.***

Xiaolong Yang https://github.com/ShawnXiaolongYang https://www.linkedin.com/in/xyang105/

https://profiles.udacity.com/p/446-***-****

Technical Skills

Languages: Python, R, Matlab, SQL, Html, JavaScript, Java Servlet, C#, VB, C, C++ Libraries: Tensorflow, NumPy, Pandas, Scikit-Learn, NTLK, Graphlab, gglot2, Flask Database: Neo4j, MongoDB, SQL server, Mysql

Software: Tableau, Octave, Anaconda, RStudio, Jupyter, Dreamweaver, Visual Studio, Myeclipse Work Experience

Data Mining Intern

June 2017 - now, MobileIron.co

Focus: Data Mining, Postgresql, Mysql, Tableau

• Used P-sql and Mysql to collect data in different product and different sources from company.

• Cleaned the data collect from different sources and found the synonyms name in different products with Open refine

• Analyzed result using R and ploted the graph using Tableau

• Applied machine learning algorithm to make recommendation Data Analyst

January 2017 – April 2017, Udacity

Focus: Data Visualization, A/B test

A/B Test - https://github.com/shawnxiaolongyang/A-B-test

• Designed an A/B test to find whether add new features would affect the courses enrollments and payments

• Analyzed the result of the former test, and design a following test. Data Visualization - https://shawnxiaolongyang.github.io/

• Analyzed Divvy Bike over 2 million lines data, found the pattern of customers’ behavior.

• Plotted the riding paths to show the distribution of customers’ behavior at time and geography.

• Applied dimple.js and d3.js to plot the charts and hierarchy bundle graphs. Research Assistant

June-December 2016, FORWARD Data Lib, University of Illinois Focus: Graph Analysis, Deep Learning, Recommendation System, Website Develop Recommendation System Design- https://github.com/shawnxiaolongyang/Researchers-Recommendation

• Developed a recommendation system to recommend valuable papers and potential researchers to users.

• Parsed and cleaned data collected from dblp in different format, transferred 5GB data in graph database Neo4j.

• Combined graph analysis algorithms Page-rank and deep learning algorithm Node2Vec for recommendation. Web-app Design- https://github.com/shawnxiaolongyang/Researchers-Recommendation/tree/master/WebRoot

• Developed a professional social network app for researchers

• Designed the UI with Bootstrap and Back-End with Java Servelt Page and Flask

• Combined the Recommendation System and Researcher Application together and published on Linux Server Data Analyst

June 2015 – May 2016, Udacity

Focus: Machine Learning, Text Mining, Data Wrangling Fraud Email Classification - https://github.com/shawnxiaolongyang/Enron-Fraud-Email-Classification

• Identified who was fraud in Enron Scandal by analyzing the 500,000 employees’ emails.

• Applied algorithms such as Gaussian NB, TFIDF, Adaboost, Random forest and KNN to classify employees.

• Verified results using Recall-Precision, used Gini importance to select features. Exploration Data Analysis - https://github.com/shawnxiaolongyang/Propsper-Loan-Data-Analysis

• Analyzed Prosper Loan over 110,000 lines data with 81 variables using exploratory data analysis.

• Explored univariate, bivariate and multivariate analysis using correlation, ANOVA, AIC via R.

• Applied dplyr to subset, validate and summarize data and ggplot2 to plot Heat map and GIS map. Data Wrangling - https://github.com/shawnxiaolongyang/Open-Street-Map-Data-Wrangling

• Assessed 1 GB Tianjin City’s Map JSON data for validity, accuracy, completeness, consistency, and uniformity.

• Assembled MongoDB for data storage and applied Regular Expression and MongoDB query in data cleaning.

• Deep-cleaned address data written in different formats, using synonymous names or with wrong postal codes. Web developer

Focus: Web development, Data Visualization

November 2014 – March 2015, Tianjin Maritime Safety Administration, China Questionnaire Design Website

• Developed a questionnaire survey website for users to test customer satisfaction

• Helped user easily design questions in a tree style frame and stored in Sql server

• Automated plotted the survey result with Chart module in C# September - October 2014, C.G Xiao’s Hospital, China Login Website

• Developed a website for Doctors to login an intelligent medicine cabinet system

• Used VB for Front End design and Mysql to save the data Education

University of Illinois at Urbana-Champaign

Computer Science-Data Science, M.S. GPA: 3.7 / 4.0 Double Major: Technology Management, M.S.

Courses in Data Mining, Cloud Computing, Applied Machine Learning, Models of Applied Statistics, Statistical Learning, Data Visualization, Data Cleaning, Text Mining and Information Retrieval, Project Management. Udacity

Data Analyst, Machine Learning Engineer Nanodegree Courses in Data Wrangle, EDA, Feature Engineer, Reinforcement Learning, Deep Learning, Data visualization, A/B test.

Contact this candidate