UNIVERSITY OF MINNESOTA, Minneapolis, MN
Carlson School of Management
Candidate for Master of Science in Business Analytics June 2019 INDIANA UNIVERSITY, Bloomington, IN
Kelley School of Business
Bachelor of Science in Information Systems, minor in Computer Science December 2016 SKILLS
• Tools: Python, R, SQL, Tableau, Hadoop, Hive, Spark, Pig, AWS, Linux, MS Excel, Java, SAP Systems
• Techniques: Predictive Modeling, A/B Test, Machine Learning, Big Data Analysis, Exploratory Analytics, EXPERIENCE
CARLSON ANALYTICS LAB, Minneapolis, MN July 2018 - Present Analytics Student Consultant
Client: Fortune 50 Technology-Enabled Health Services Business
• Utilize data engineering techniques and machine learning algorithms to automate data mapping process of 2.2+ PB raw data into standardized format, which reduces mapping manual effort from 2 weeks to less than 1 day for each data source.
• Perform big data analysis of incoming data using Hive and Spark in order to improve data accessibility and usability for data engineering team.
Client: Leading Hospitality and Entertainment Business in Midwest
• Built dynamic and static hotel occupancy prediction models using Scikit-Learn and Keras in Python to maximize revenue and improve forecast accuracy by 5% with random forest model.
• Delivered a new metric about customers worth by analyzing customer behaviors using statistic model in order to develop marketing promotions and improve customer retention. Client: Mall of America (MOA)
• Performed market basket analysis with 1M transaction records across 3 years using R to identify co-purchased products and designed product bundles to maximize gift store sales.
• Formulated seasonality time series model to identify seasonal products and predict required inventory to increase stores profits, which achieved an overall accuracy above 90%.
• Utilized k-means clustering analysis in Python to analyze cashier performances across stores to improve staff arrangement for better customer experience.
CIeNET TECHNOLOGY CO., Beijing, China
Software Development Engineer in Test July 2017 - April 2018
• Automated software development QA testing by weekly converting 100+ manual test cases into scheduled scripts, resulting in 50% reduction in testing time.
• Translated technical test data output into understandable descriptive statistics, which improved test efficiency and enabling stakeholders to make decisions.
• Led a team of 5 developers using Agile test driven development, resulting in faster product feature development and enhanced client ownership.
DATATANG TECHNOLOGY CO., Beijing, China
Business Data Analyst Intern February 2017 - March 2017
• Performed image data analysis for vehicle autopilot system using Python in order to automate image data labeling process, resulting in reducing 25% manual labeling effort.
• Optimized data query process using SQL, which helped company save 30% time on data extracting and transforming process.
• Improved enterprise data end to end processing including collection, annotation, and customization of voice data for data democratization to university research labs.
Predictive Modeling: Performed time series (ARIMA) model to predict California house price and unemployment rate using Python scripts via TabPy API and visualized results in Tableau. Big Data Analytics: Developed network analysis with Amazon co-occurring purchase data using Spark and Spark GraphFrames, helped provide better product bundling; visualize result using Gephi for further analysis. Exploratory Analytics: Identified business consistency, customer loyalty and demand distribution of a coffee shop using statistic model with 220k+ transaction data and performed association rules and clustering models to provide data-driven recommendation.