EDUCATION

University of California, Santa Barbara | Sep 2018 - Mar 2022
BS in Statistics and Data Science & Applied Mathematics

  • Major GPA 3.8/4.0
  • College of Letter Science Honors Program

Courseworks:

  • Statistics: Regression Analysis, Statistical Data Science, Machine Learning (Graduate Level), Bayesian Data Analysis, Time Series (Graduate Level), Stochastic Process (Honors)

  • Mathematics: Advanced Linear Algebra (Honors), Numerical Analysis, , Real Analysis, Ordinary Differential Equation, Financial Mathematic

  • Computer Science: Programming Methodology with Java, Data Structure and Algorithm, iOS Development

RESEARCH

Hyperparameter Tuning in Deep Learning - Independent Research                              

Advisor: Nils Detering, Associate Professor

  • Evaluated the structure (nodes, layers, activation functions), learning process (gradient descent, backpropagation), and expressive power (Universal Approximation) of Feedforward Neural Networks
  • Simulated Feedforward Neural Network on classifying handwritten digits using TensorFlow, and fine- tuned hyperparameters such as width, depth, learning rate, batch size to maximize classification accuracy

PROJECTS

Predictive Analysis on 2016 U.S. Election – Machine Learning                         

Aggregated 2016 U.S. election data and 2010 census data; Built logistic regression, random forest, boosting model to predict the county-level winning candidate; Clustered counties with similar census features; Analyzed predictive features and their association with candidacy preference with K-Means algorithm and PCA method

Spotify Time Series Analysis – Time Series                                                 

Collected 160k+ songs data from 1921 to 2020 with Spotify API; Analyzed the relationship between characteristics and popularity of songs; Forecasted the energy index of top popular songs each year with time series model

EXPERIENCES

UCSB Movement Data Science Lab
12/2021 - Present | Santa Barbara, CA
Research Assistant - Python Developer

  • Constructed Postgre databases with temporal and spatial data for animal trajectory research
  • Developed data modeling and visualizations python library VASA for analyzing the relationship between non-pharmaceuticals interventions (NPIs) mobility metrics and Covid-19 virus transmission

UCSB Probability and Statistics Department
09/2021 - 03/2022 | Santa Barbara, CA
Undergraduate Learning Assistant - Data Science

  • Tutored students on data retrieval, cleaning, and visualization using Python Pandas, matplotlibs, altair
  • Tutored students on Bayesian Statistics and Markov Chain Monte Carlo implementation in R

DiDi Global Inc.
International Business Group - Hongkong Team
01/2021 - 04/2021 | Guangzhou, CN
Software Engineer Intern

  • Automated data cleaning pipeline across millions of raw records using Python, which saved 45 hours of manual work per month
  • Optimized SQL queries and code logic, which reduced run time by 32%
  • Communicated with the marketing team to understand business needs, developed the business intelligence dashboards from scratch, which allowed 18 team members to make data-driven decisions

AppFolio, Inc.
06/2020 - 09/2020 | Santa Barbara, CA
Software Quality Assurance Engineer Intern

  • Collaborated with a 5-people agile development team to ensure low bug rate during upgrading reports framework, which enhanced the usability and accessibility for diverse clients
  • Leveraged exploratory, black/white box, and regression testing on the migration of 150 reports, which reduced 50% of customer-reported bugs
  • Automated 30% test cases with Selenium WebDriver, which advanced the completion of reports migration project by 2 weeks

UCSB Orientation Program
04/2019 - 08/2019 | Santa Barbara, CA
Orientation Leader

  • Served as an official representative of the university; communicated with students and parents on topic related to academic advising, student life, and campus recourses

INVOLVEMENTS

UCSB The Bottom Line Newspaper
05/2020 - 05/2021
Editorial Board | Web Editor

  • Managed the Bottom Line website as an editorial board member; analyzed user behavior and content consumption to faciliate user acquisition and engagement; integrated Covid-19 tracking widget as a reliable source for monitoring local pandemic situation

AWARDS & QUALIFICATIONS

SKILLS SUMMARY

  1. Technical: Proficient in Python, R, SQL; Intermediate Java, Tableau; Familiarity with C++
  2. Teamwork: Facilitated work in both small size software development team (6 people) and large size orientation staff team (30+ people)
  3. Communication: Extensive experience in effective and efficient communication with peers, parents, professors, and colleagues
  4. Language: Native Chinese; Fluent in English; Conversational Spanish