Wilson Chen
***********@*****.*** www.linkedin.com/in/wilsonhc https://github.com/xchen715 Newark, CA
Summary
Proven ability in Python/R/SQL programming and strong analytical skills to solve complex problems.
A highly motivated self starter has experience in collecting, researching, and analyzing data; training, testing, and deploying models; and reporting business metrics and performance.
Technical Skills
Language: Python, R, SQL/MySQL, Linux/Unix.
Data Science: data analysis, data visualization, data mining, natural language processing (NLP), artificial intelligence, machine learning.
Software: Tableau, Amazon Web Services (AWS) EC2/ S3/ RDS, Apache Spark, Apache Hive, Hadoop, Google Cloud Platform (GCP) storage, Excel, noSQL database (Fire Base), git/github.
Certification: Applied Machine Learning (Emeritus, Columbia Engineering), Data Scientist with Python (DataCamp), SQL Database Fundamentals (Microsoft), Chartered Financial Analyst (CFA) level one passed (CFA Institute).
Profession Experience
Research Assistant - University of Maryland Jun 2018 - Oct 2018
Designed creative approaches and wrote programs (Python/R) to acquire and to process data from various sources.
Applied machine learning, artificial intelligence (AI), and data science techniques (feature engineering/dimension reduction/imputation) to develop algorithms predicting points differentials in games.
Identified three key factors in games by implementing statistical modeling and machine learning modeling/algorithms on 10+ data sets with different combinations of features.
Developed a real-time predictive end-to-end system on Amazon Web Services (AWS) Amazon Elastic Compute Cloud (EC2) and Relational Databases Services (RDS).
Self-learned to design data pipeline architecture and web crawling tools and applied them into practice in two weeks.
Course Projects
Principal Financials News Text Mining – Capstone Project
Researched six machine learning algorithms (logistic regression/SVM/Naive Bayes/decision tree/random forest/gradient boosting) and implemented natural language processing (NLP) techniques and libriries (nltk/gensim) to develop a news topic classification model with 73 percent accuracy.
Used Python data science libraries (scikit-learn/pandas/numpy/nltk/matplotlib) to process and analyze 20+ data sets.
Built visualizations to convey analytical solutions/business metrics to the internal team as well as external clients in presentations.
Airbnb Popular Listing Prediction – Data Mining and Predictive Analytics/Big Data and Artificial Intelligence (AI)
Researched on machine learning algorithms and developed a classification model that has 85 percent accuracy on recognizing popular hosts.
Cleansed and transformed 100,000+ rows of numerical, categorical, and text data for machine learning modeling.
Documented recommendations and features that impact the popularity and reported results to a panel of professors.
Master Program Ranking Database – Database Management
Designed and developed SQL databases frameworks in Microsoft SQL Server Management Studio.
Created a real-time Tableau dashboard accessing data in SQL databases.
Developed teamwork/collaboration skills to work in a five people cross functional team.
Academics
Master of Science in Business Analytics - University of Maryland, College Park Maryland Dec 2018
Database Management, Data Mining & Predictive Analytics, Big Data & Artificial Intelligence (AI), Python
Bachelor of Arts in Business Administration - National Chung Cheng University, Chiayi Taiwan Jan 2016
Statistics, Financial Analysis, Investments, Advanced Financial Management, Economics