Meiying (May) Xiang

adbhl2@r.postjobfree.com 617-***-**** Worcester, MA

Educational Background

Worcester Polytechnic Institute, USA Jan 2018- Dec 2019 M.S in Information Technology (Specialization: Data Science) GPA: 3.41/4.0 Central South University of Forestry and Technology, China Sep 2013- Jun 2017 B.A. in Economics, GPA: 3.67/4.0

Hunan Province Outstanding Graduate Award (top 1%) Rank: 5/278 First-Class Scholarship for Academic Excellence (top 1%) Skills

Software Packages: Linux, Shell, Tableau, Visio, Axure, PowerPivot, EViews, SAS Programming: Python, R, Java

Database Hadoop and HDFS, Hive, PostgreSQL, MySQL, SparkSQL, Oracle, Microsoft Access Work Experience

Airbus Group Data Scientist May 2019-Sep 2019

u Improved database performance by creating a unified ODS database for the HR department using MySQL and developed GUI in Microsoft Access, highly improve the work efficiency after implementation. u Performed ETL to cater daily data requirements of the department by using MySQL and Python. u Developed dashboard for the operations department using MySQL and Tableau by analyzing historical data. u Used Python to build Logistic Regression and Radom Forest Model for the talent project, found the significant factors of talent projects, helped HR to optimize the rules for the talent project. The accuracy of the model is 91%. Baidu.com, Inc Data Analyst May 2018-Aug 2018

u Performed analytics on the user data retrieved from the HiveSQL server, did ETL and data visualization among different countries by using HiveSQL, Tableau, and Excel, wrote weekly reports of the operational analysis. u Developed corresponding operational strategy by analyzing user data. The number of users increases by 47% during the internship.

u Collected and analyzed APP crush or bug data, and user feedback to improve the app and add useful functions. u Extracted data using MySQL and Python and performed data cleaning in Python regular expression. China Construction Bank Operations Analyst Jun 2017-Nov 2017 u Using advanced excel functions to merge and clean large data set by MySQL. u Performed data visualization by using Tableau and Excel, including weekly and monthly international trans- action data, generated weekly reports based on data analysis. Project & Activity

Machine Learning for NYC Taxi Profitability Jan 2019-May 2019 u Performed source data cleansing and ETL to R and Python data frame. u Conducted variable selection in LASSO regression analysis to enhance prediction accuracy. u Built profitability models such as logistic regression, KNN, QDA, Cross-validation, and have an 88% accuracy. Social web mining on Twitter Jan 2019-Feb 2019

u Collected real-time data of Twitch streaming by twitter steaming API using Python, then analyzed popular tweets and extracted hashtags and user mentions.

u Conducted k-means clustering in Python to find the most popular streamer in Twitch. Application Development on Android Studio for Clevo Co. Jan 2018-May 2018 u Analyzed user demand based on the business needs of the Clevo. u Established the ODS data structure based on the relational database and uses VISIO to build the ER diagram. u Wrote data dictionaries and data interface documents based on user needs and business scenarios. u Programmed the application in Android Studio using Java and SQLite.