I am a

Data Scientist

Fascinated by using machine learning solve problems in different contexts, I learned all kinds of data science skills and working hard to be a great data scientist.

Top Kaggler

To validate my machine learning skills, I actively compete in different competitions and keep myself reinforcement learning. After winning 4 solo medals, now I rank top 0.5% worldwide.

Financial Analyst

With a few years of experience in financial industry, I have passed all CFA exams and keep earning my tuition and traveling expense by investing in derivatives.

World Explorer

During my gap year in 2016-2017, I backpacked 25+ countries in 5 continents. I keep exploring this wonderful world and also exploring myself on the way.

Featured Project

User In-app Purchase Prediction

An end-to-end machine learning model pipeline, from data extracting, preprocessing to ultimate modeling.
[Data Cleaning & Wrangling, EDA, Feature Engineering, Gradient Boosting Classifier]

Toxic Comment Classification

Using different techniques to preprocess text data, built text classifiers to recognize toxic comments.
[NLP, TFIDF, SVM, Naive Bayes, Linear Regression, Random Forest]

U-Net For Organ Segmentation


An architecture based on Convolutional Neural Network (CNN) to make segmentations for multiple organs from CT images.
[Deep Learning, Computer Vision, CNN, Image Segmentation, 3D Images]

MLator - An Automated Manga Tranlation Platform

Automate the manga translation based on a series of machine learning models and APIs, a whole project for a start-up product.
[Business Plan, Product Analytics, OCR, Object Detection, Machine Translation]

Smartphone Human Activity Recognition

Using SparkML, deploy a paralleled machine learning model on AWS EMR to recognize human activity, based on data from smart devices.
[Distributed Computing, MongoDB, Spark, Map Reduce]

Isolation Forest

Following the original papers, reproduce the anomaly detection algorithm from scratch, with improvement on noise resistance.
[Python, Anormaly Detecting, Object-oriented Programming]