Data Analyst Social Media

Tuo Wu

**** * ***** ****** *** ***, Arlington VA

******@*****.***

EDUCATION

Georgetown University, Washington DC Anticipated May 2020

• MS, Data Science and Analytics GPA: 3.67 / 4.0

• Relevant Courses: Machine Learning, Massive Data Fundamental, Data Analytics, Data Visualization, Deep Learning The University of Iowa, Iowa City, IA August 2014 - May 2018

• B.S, Mathematics and Computer Science Minor; B.B.A Finance

• Relevant Courses: Data Mining, Python, Algorithm, Data Structure, Numerical Analysis SKILLS

Technical: Python, R, SQL, AWS, HTML, Tableau, A/B Testing, NLP, Hadoop, Spark, Tensorflow Language: English(Fluent), Mandarin(Native)

PROFESSIONAL EXPERIENCE

The Center for Security and Emerging Technology Washington DC Data Analyst Nov 2019 - Present

• Retrieved 1M rows of repositories’ information based on certain keywords from Github via Python(Pygithub) in order to understand which organizations are doing research about machine learning

• Queried and manipulated data (5+TB) from Google BigQuery and relational databases using SQL Wendol Co., Ltd. Zhejiang, China

Co-Founder May 2018 – Present

• Scraped and analyzed Amazon reviews using Python (Scrapy) to investigate customers’ preferences and tailor products based on actionable insight leading to a monthly revenue growth to $60,000 within one quarter

• Conducted funnel analysis to explore actionable insight of conversion rates, directed pricing optimization for products, and increased monthly revenue by 15%

• Saved 10% on advertising costs by exploring keywords which accurately find target customers on different social media

• Collaborated with cross-functional partners to deliver products one week ahead of schedule Negotiation Works Washington DC

Data Analyst March 2019 – Present

• Collaborated with instructors to design 68 survey questions as a data source and conducted descriptive analysis to evaluate participants’ performance via Python(Numpy, Pandas)

• Performed topic modeling and text mining techniques with Python (NLTK) to analyze survey questions and optimize lecture design which increased the number of participants by 15%

• Conducted different hypothesis testing to prove if lectures are useful, visualized and presented analysis results by Tableau to sponsor and receive $20,000 donation for the first phase Pingan Technology Co., Ltd Shanghai, China

Data Analyst May 2019 – August 2019

• Designs and develops SQL queries for extracting information, trends, insights and metrics from financial data

• Prepared large-scale datasets with high availability for building predictive models by cleaning, merging from different tables and computing additional financial variable using SQL

• Efficiently loaded 1 million rows of data via Amazon RDS database instance into local Mysql ACADEMIC PROJECTS

Prediction of Blood Cell Types October 2019 – December 2019

• Experimented with CNN models using different parameters (Dropout) and regularization to predict blood cell types with TensorFlow, achieving 81% classification accuracy

• Implemented a Python Program to load and augment 12,500 images of blood cells via Tensorflow

• Converted images from RGB to HSV and performed color segmentation which extracted useful cells from image via Python(CV2)

Airbnb Price Analysis October 2018 – December 2018

• Applied predictive model to help landlord set smart price for their house on Airbnb and efficiently received orders.

• Scraped 200,000+ rows of data from Airbnb, and implemented data extraction, data transformation and table merge efficiently via Python(Pandas)

• Performed hypothesis testing about the relationship between house features and price of houses on Airbnb

• Directed feature selection and built a random forest predictive model, evaluating the model with roughly 79% accuracy for each group via Python(h2o); trained and fine-tuned the model to find optimal results which increased accuracy by 2%

Contact this candidate