Clark Li Email & Phone Number

California, United States

Mountain View, California, Us

A 500 hr+ immersive project-based curriculum that emphasizes Python, SQL, Statistics, Machine Learning, and Data Processing. Select Projects:Airbnb Review Summarizer - Natural Language Processing (NLP)• Utilized Python NLP packages (SpaCy, NLTK, Textblob) to design an aspect detection and sentiment analysis model that extracts relevant information from Airbnb reviews to enhance user booking experience.• Built the complete ETL pipeline to warehouse review data on AWS PostgreSQL using SQLAlchemy and Pandas; and developed a Flask web app for collecting and storing validation data. Ride Sharing Customer Churn Prediction• Conducted extensive EDA and feature engineering on ride sharing data and built statistical models to predict customer churn using logistic regression, random forests, and gradient boosting models in Python-Sklearn.• Constructed confusion matrix and profit curves based on an 80% model test accuracy score and provided feature importance analysis and action recommendations.Amazon Review Sentimental Analysis - NLP• Performed sentimental analysis on subset of Amazon review data to identify latent topics that reflect people’s feelings within positive and negative reviews.• Implemented Naive Bayes model on AWS EMR using Spark-python API (PySpark) and TF-IDF vectorization technique supported by Natural Language Toolkit (NLTK).

Toronto, On, Ca

• Utilized SQL and Excel to detect data anomalies from predictive models and formulate actionable insights to present to various stakeholders including traders, technology teams, and senior management. • Developed desktop analytics and dashboard reports using SQL and VBA to support new business initiatives • Received two Quarterly Achievement Awards for the development of analytic tools that benefited team of 20+ from boosted efficiency and for exceptional work dedication during times of staff shortage

Toronto, Ontario, Ca

• Used Javascript to automate the daily Profit & Loss reporting process for business from a 2-hour manual procedure to an instantaneous solution by building online dashboards linked to centralized database.• Restructured the existing database using Python, Perl, and MySQL to improve ETL within data flow pipeline.

Toronto, Ontario, Ca

• Built and maintained Excel tools to help interest rate derivative traders hedge trade positions by incorporating delta sensitivity calculations, interest rate swap pricing• Monitored daily front office regression tests; developed Perl scripts to extract and automatically email test results directly to related personnel, thus allowing test problems to be detected more efficiently

New York, Ny, Us

• Reverse-engineered source data generation logic in SQL, Java to analyze and close regulatory compliance gaps• Designed test scenarios and enhanced testing framework for client data validation using VBA and VBScript.

Bachelor'S Degree, Mathematics/ Financial Analysis And Risk Management, Co-Op

Education record

Immerse Data Science Program