Xiaonan Liu
*** * **** **. ************, PA***** adkaqz@r.postjobfree.com 336-***-**** https://github.com/xiaonan6 EDUCATION
University of Pennsylvania, School of Engineering and Applied Science Philadelphia, PA Master of Science in Engineering in Data Science May 2022 Cumulative GPA: 4.00/4.00; Award: Wharton Customer Analytics & Essity Datathon 2nd Place winner Relevant Coursework: Machine Learning, Big Data Analytics, Database & Info System, Deep Learning, Computational Linguistic Wake Forest University Winston-Salem, NC
Bachelor of Science in Mathematical Statistics; Minor: Psychology May 2020 Major GPA: 3.94/4.00; Cumulative GPA: 3.88/4.00; Award: Dean’s List; Summa Cum Laude; Departmental Honor Graduate Relevant Coursework: Multivariate Statistics, Probability, Statistical Learning, Statistical Inference, Linear Algebra, Real Analysis SKILLS & ATTRIBUTES
Programming Languages: SQL, NoSQL, Python (sklearn, matplotlib, Keras, pandas, NLTK), Java, R, LaTeX, SPSS, Tableau Additional: Data ETL, Data Mining, A/B Testing, AWS Cloud, Microsoft Azure Cloud, Apache Spark, and PyTorch DATA COMPETITION & PROJECTS
Movie Success Prediction Philadelphia, PA
Business Analyst (Python, Apache Spark) November 2020 – December 2020
Extracted and cleaned 26,000,000 reviews from 270,000+ users on 45,000 movies from TMDB open API and GroupLens
Conducted exploratory data analysis and rich visualizations to explore the relationship between features and response variable
Built machine learning pipelines with feature encoding, Word2Vec feature engineering, and gradient boosting machines
Predicted movie success (metrics: raw profit, ROI, rating), and provide data-driven insights to support investment decisions Pokémon Image Classification Philadelphia, PA
Machine Learning Engineer (Python) November 2020 – December 2020
Utilized Convolutional Neural Network and Transfer Learning (ResNet-50, VGG16) to perform Pokémon Image Classification
Generated augmented images of each Pokémon to improve the model performance COVID-19 Tracker Philadelphia, PA
Data Engineer (Python, MySQL, JavaScript, AWS Cloud) October 2020 – December 2020
Pre-processed COVID-19 data, performed entity resolution, and populated the database using AWS RDS with MySQL engine
Designed database with ER model, translated ER diagrams into relations, and built a program to update the database daily
Wrote and optimized SQL queries to retrieve the desired output based on user input value
Developed a web application for the COVID-19 database with user-interactive map of COVID-19 cases distribution in U.S. PROFESSIONAL & RESEARCH EXPERIENCE
Wake Forest University School of Business Winston-Salem, NC Research Assistant / Data Analyst (Python, R, Microsoft Azure Cloud) February 2020 – Present
Developed program to scrape customers’ review texts on Amazon and public posts data from Instagram
Utilized high performance computing clusters to wrangle over 300,000,000,000 records of data for years 2017-2020
Analyzed relationship between the review text and satisfaction using natural language processing, visualized the relationship by word cloud, and classified the product attributes commented on with machine learning techniques
Processed photo characteristics data using Python and Microsoft Azure API to analyze popularity of posts Spatiotemporal Analysis Project, Wake Forest University Winston-Salem, NC Honors Researcher (R) July 2019 – May 2020
Processed data of temperature, precipitation, and potential explanatory variables of detected cases of histoplasmosis
Designed program to visualize spread of diagnosed cases of histoplasmosis in U.S.
Fitted ZIP model, occupancy model, time series, and auto-logistic model to account for unreported cases of histoplasmosis
Estimated current endemic area of histoplasmosis and drew current map for endemic area of histoplasmosis LEADERSHIP ACTIVITIES
Wake Forest University Resident Life and Housing Winston-Salem, NC Resident Advisor August 2019 – May 2020
Planned and executed 28 activities for community per academic year, including floor dinner and career panel
Communicated and collaborated with teams to hold community events, such as Self-care Sunday The National Mathematics Honorary Society Pi Mu Epsilon at North Carolina Lambda Chapter Winston-Salem, NC Treasurer August 2019 – May 2020
Contributed to activity planning including sale of study guides and mentor lunch each semester
Prepared and submitted budget for undergraduate research colloquium, faculty research talks, and career panel