YILUN SUN

Los Angeles, CA • adkdmt@r.postjobfree.com • 206-***-**** •https://www.linkedin.com/in/yilunsunusc/ •https://github.com/yiluns EDUCATION

University of Southern California, Marshall School of Business – Los Angeles, CA December 2021 Master of Science in Business Analytics (STEM) 3.95/4.0

• Coursework: Data Driven Decision Making, Statistical Computing and Data Visualization, Advanced Regression Analysis, SQL Databases, NoSQL Databases in Big Data, The Analytics Edge: Data, Models, and Effective Decisions University of Washington – Seattle, WA March 2019

Bachelor of Science in Economics, GPA: 3.7/4.0 (Dean’s List)

• Coursework: RStudio Basics, Statistical Data Interpretation, Econometric Applications, Consumer Behavior Analysis ANALYTICAL PROJECTS

Titanic Machine Learning Competition - Kaggle Fall 2020

• Utilized classification models (Logistic Regression, Support Vector Machine, Random Forest, KNN, XGBoost) to predict Titanic passengers’ survival status based on features given and engineered

• Performed Randomized Search CV and Grid Search CV to fine-tune models’ hyperparameters; final XGBoost model had an accuracy score of 84.92% on training dataset and 78% on testing dataset Humana/Mays Healthcare Analytics Case Competition, USC – Los Angeles, CA Fall 2020

• Landed in 2nd place out of over 280 teams

• Utilized feature engineering (Group Binning and Ranking, Weighted Metrics) and selection to extract key features from over 800 original features and built an XGBoost model to predict Medicare members most likely experiencing transportation issues

• Employed factor analysis to conclude with 5 most relevant features and K-means to find 4 groups most at risk and proposed specific solutions for each group

• Presented findings and business recommendations to Humana stakeholders and Mays Business School faculty IBM Data Science Capstone Project Winter 2020

• Exploratory project to cluster Toronto’s neighborhoods based on each neighborhood’s popular venue type

• Made API calls to Foursquare to retrieve location data, extracted and converted json files to DataFrames, utilized Pandas to scrape and clean up online tables, Folium to visualize and mark neighborhoods, and K-Means to cluster neighborhoods SKILLS & INTERESTS

• Programming: Data Manipulation (Python: Pandas, NumPy), Machine Learning (Scikit-Learn, PyTorch), Database Management (SQL, NoSQL), Web Scraping (BeautifulSoup)

• Visualization: Python: Matplotlib, Seaborn, ggplot, Plotly, Folium, Tableau

• Machine Learning: Supervised Models: Linear, Logistic Regression, Random Forest, XGBoost, K-Nearest Neighbor, Support Vector Machine. Unsupervised Models: K-Means Clustering

• Interests: Electric Dance Music, Gaming, Snowboarding, Basketball, Reading EXPERIENCE

Lani Cao Law Office – Bellevue, Washington 2019 – 2020 Finance Intern

• Utilized a linear programming model using Excel to implement changes on employees’ schedules and decreased firm’s salaries expense by 10%

• Gathered personal information of 400+ clients and built client database using Excel; suggested advertisement location and activity based on customers’ locations and brought in 3 more clients and $1000 averagely per month LEADERSHIP EXPERIENCE

China Entrepreneurship Network (CEN), University of Washington – Seattle, WA 2016 – 2019 Director of Finance Department

• Managed annual team-building activity budget of $5,000 for sixty members with two team-building activities delivered under budget; negotiated sponsorships totaling over $20,000 and accommodations for invited event guests