Elizabeth Lee

Highly accurate and experienced Software Engineer/Data Scientist adept at collecting, analyzing, and interpreting large datasets, developing new forecasting models, and performing data management tasks. A result-oriented professional with over 8 years’ experience in software development and enhancement, service delivery and relationship management within the technology domain.

Skills: Pyspark, Python(Pandas, Pytorch, Numpy, Scipy, Seaborn, Matplotlib, Plotly, Keras, Tensorflow), SAS, Java, Git, MySQL, Oracle
Exposure: JavaScript, R, Scala, PostgreSQL, SQLite, C#, html5, CSS

Data Scientist

Feb 2019 - Present · 4 yrs 1 moFeb 2019 - Present · 4 yrs 1 mo

● Built an automatic defect detection tool based on statistical analysis and predictive data modeling such as Gradient Boosting using Python saving $11M annually.
● Implemented several dashboard visualization applications to help customers to improve the manufacturing process using Python language, Dash, and Streamlit framework, leading to hundreds of new users.
● Automated all data visualization reports of existing machine learning programs using python saved approximately 50 hours of generating reports.

Software Engineer

Nov 2017 - Feb 2019 · 1 yr 4 mosNov 2017 - Feb 2019 · 1 yr 4 mos

● Created dozens of new features of the web-based Manufacturing Operating System using Java, improving UX.
● Fixed bugs from the existing web-based system and implemented enhancements improving web functionality and speed by 20%.
● Created and improved documentation to help business users understand the system more easily saving about 10 hours weekly of troubleshooting guiding end-users.

BA in Statistics, University of California, Berkeley                                                                                                    Graduated in June 2015

MS in Computer Science, Arizona State University                                                                                                    Graduated in Feb 2023

Relevant Courses: Software Security, Artificial Intelligence, Software Verification and Validation ,Mobile Computing, Advanced Software Analysis and Design, Data Processing at Scale, Statistical Machine Learning, Data Mining, Data Structure and Algorithms, Structure, and Interpretation of Computer Programs, Reproducible and Collaborative Data Science, Computing Data, Modern Statistical Prediction and Machine Learning

PROJECT WORK

Hand Gesture Recognition for Smart Home                                                                                                                                            2020

• Developed a python program that identifies videos of hand gestures for smart home application using CNN(convolutional neural network) resulted saving hundreds of hours of manual classification.

NYC Hot Spot Analysis                                                                                                                                                                                      2020

• Developed a program that identifies statistically significant spatial hot spots in New York City using Yellow Cab taxi trip records using Scala and Apache Spark saving thousands of hours of finding the hot spots manually.

Handwritten digits classification                                                                                                                                                                  2020

• Developed a program that classifies images of handwritten digits using CNN and naive bayes algorithm in Python saving hundreds of hours of manual classification.

Spam Filtering                                                                                                                                                                                                      2014

• Developed a Spam Filtering program that classifies whether an email is a spam or non-spam using Random Forest in Python resulting in above 98% accuracy and saving hours of time to filter spam emails and protecting from scams.