Hi, this is Minchen!

Welcome to my site! I'm a passionate data scientist, keen on wrestling with complex data and building better products through data-driven solutions.

Now I'm a Business Intelligence Engineer at AWS. I previously worked as a Data Scientist at Bird, a start-up that runs the largest scooter-sharing business in US. At Bird, I worked on building production-level ML model to improve operational efficiency, and analyzing large scale rider behavior data to support product teams in decision making. Prior to Bird, I worked as a Data Scientist (co-op) at Dictionary.com, where I focused on improving company online advertising revenue by leveraging ML algorithms and ad performance analysis.
I got my Master's degree in Data Science (MSDS) at the University of San Francisco, where I have developed a strong programming and statistics skill set and refined my problem solving skills.

On this page, I'd like to share some interesting projects that I have completed during my graduate school. Thank you for taking a look and please feel free to contact me via email or LinkedIn for any question.

Featured Projects

View

Manga Translation Web App Product

Develop an end to end website platform that automatically converts Manga image (in Japanese) into English images from scratch.

(Python, Back-end, Front-end, Deep Learning, Deploy)[more]

View

In App User Purchase Prediction

Build data pipeline to process large-scale data (over 50GB) and predict user activity.

(Python, AWS, Big Data, Feature Engineering)[more]

View

Smart-phone based Human Activity Recognition

Design and Build a distributed data pipline to classify human activity.

(ETL, Data Pipeline, AWS S3, AWS EMR, MongoDB, SparkSQL, SparkML, PySpark)[more]

Machine Learning and Statistics

View

Online Auction Bidder Classification

(Python, Random Forest, Gradient Boosting, Feature Engineering, Grid Search)[more]

View

Movie Recommendations

(Python, Matrix Factorization, Collaborative Filtering, Gradient Descent Optimization)[more]

View

Click Through Rate Prediction

(Python, Random Forest, Feature Engineering, Mean Target Encoding)[more]

View

Bankruptcy Rate Prediction With Time Series

(R, SARIMAX, VARX, Holt-Winters)[more]

Natural Language Processing

View

Twitter Sentiment Analysis

(Python, AWS, Tweepy, VaderSentiment, Jinja, Flask)[more]

View

BBC Article Recommendations

(Python, AWS, Word2vec, Word Embeddings)[more]

My Skills