Xiao(Shawn) Xie

*** ******** ** *******, **, ****4

adb5o4@r.postjobfree.com 240-***-****

EDUCATION

University of Maryland, Robert H. Smith School of Business College Park, MD Cumulative GPA:3.8/4.0 Master of Science in Business Statistics, Specialization: Data Analytics

• Participated in the Smith Datathon Market Competition, received first prize among 52 competition groups

• NLP: Performed sentiment analysis and built LDA topic model towards luxury hotel reviews in Expedia

• Predicted customer purchasing by building classification and regression models for Google Store TECHNICAL SKILLS

• Proficient in exploratory and prescriptive data analysis: Python, R(tidyverse), Advanced Excel Functions

• Proficient in classifying and clustering analysis (Machine Learning): Python(Scikit-Learn), SAS

• Proficient in Natural Language Processing: Sentiment Analysis, LDA topic model, Python (NLTK Keras)

• Proficient in Interactive Data Visualization: Tableau, PowerBI, Python (Seaborn, Matplotlib)

• Proficient in Database management and Database design: Star Schema, Snowflake, MS SQL (SSDT) – SSAS, SSIS, SSRS

• Advanced in Extraction, Transform, Load: Alteryx, Informatica PowerCenter, Talend ETL

• Advanced in Agile Scrum and DevOps methodologies in software development life cycle Epic Feature, PBI, Tasks, time, left over items

EXPERIENCE

House Price Predicting for Residential Homes in Iowa(4% out of 4852 teams) College Park, MD Data Scientist Sep 2019 – Nov 2019

• Cleanup Kaggle data for training requirements including cleaning missing values, filtering the invaluable data, and deleting the outliers log-transformed the sale price.

• Conducted exploratory data analysis to explore the variable distribution and relationships using Python.

• Performed the Feature engineering analysis by adding 3 house index features and selected 15 essential features using Boruta package in R – box chart.

• Developed 6 regression models(lasso, ridge, GBM, lightgbm, etc.) to predict housing price and used grid- search function to optimize the hyperparameters for each model, decreasing the RMSE to 1.49. Tencent Group (Top 2 Chinese Internet Company) Guangzhou, China Data Analyst Jun 2019 – Aug 2019

• Supported product team by analyzing trends of the 2 Music Streaming App using SQL and Tableau and created daily and weekly user visualization reports based on 300 billion users’ pools.

• Built the ETL workflow using SQL to assess and document the data flow from user interface to revenue, which promoted product function adjustment and increased the visit of users by 10%, increasing revenue by 7%.

• Found 227 possible churn high-end users (who had spent more than $150,000 on the APP) by analyzing the user activities and user consumption records using SQL, which reduced 10% of user recalling cost.

• Checked the data integrity and accuracy of new user activity tables by inspecting the event tracking system which contained more than 1000 event trackers using sniffer packet, facilitating the use of new tables. Tongfu Digital Engineering (Online Animation Platform Startup) Wuhan, China Cofounder, Marketing Analyst Jan 2016 – May 2017

• Initiated the business plan and worked with the marketing team, animation team, and web development team to build an online animation platform to show original animations.

• Identified 4 target groups by analyzing user browsing and watching data using excel and personalized advertised to different user groups, which improved the subscription and revenue by 45%.

• Built a user growth team and launched 11 online and offline events, increasing the user amount by 30000.

• Led the fundraising pitch, negotiated with multiple venture capital, raised $200,000 for the company.

• The team won the National Silver Price (6/4532) in the 2016 China Youth Entrepreneurship Competition.

Contact this candidate