Sign in

Data Scientist

Long Island City, NY
March 25, 2019

Contact this candidate



I am highly passionate about leveraging massive data to drive executable business solutions. I have 2+ years’ coding experience, 1-year industry experience in statistical analysis and data science field Languages: Proficient in Python (Pandas, Numpy, sklearn and etc), SQL, Linux Business Intelligence: Tableau, D3.js

Data Science: Statistical analysis, Machine Learning (Decision Tree, Random Forest, Clustering, Neutral Network and etc), NLP, TensorFlow, PyTorch, Spark

Others: Excel, PowerPoint


Fordham University, New York Dec 2018

M.S in Data Analytics, data science track – GPA 3.65

• Related courses – Machine Learning, Data Visualizations, Financial Programming and etc University of North Carolina, Chapel Hill Dec 2015 B.S. in Mathematical Decision Science - Statistics PROFESSIONAL EXPERIENCES

CollectorIQ – New York, NY May 2018 – present

Data Scientist

• Build regression models with massive amount of data to provide analytical insights into valuations and liquidity level of art collectibles (mainly paintings and sculptures)

• Implement NLP technique to conduct sentimental analysis on massive text data

• Design and visualize models/insights/results with Tableau

• Deliver bespoke analytics to non-tech-background senior stakeholders regularly on using data science to provide opportunities for company development

Vendome Global Partners – New York, NY June 2016 – Nov 2016 Investment Banking Analyst

• Composed teaser and CIM; performed valuation analysis by building financial models

• Conducted in-depth beauty and skincare market industry research, producing industry/company analysis reports and sourced acquisition opportunities

• Assisted in Aurum Holding’s acquisition of Mayor, a prestigious jewelry retailer PROJECTS

University Endowment Use-Case Analysis with Selective Learning Dec 2018

• Crawled Twitter followers of Universities with Python Twitter API

• Built random forest, SVM, gradient boosting, deep neutral network classification applications to analyze whether universities poorly use endowments fund. Measured performance with MSE and R-square

• Used selective learning to improve classifiers’ performance Divvy Shard Bike Big Data Analysis with Spark March 2018

• Built Spark and SparkSQL-based models to analyze time-series Chicago Divvy sharing bike usage data

(~4GB in size)

• Implemented machine learning models to predict future bike usage given weather forecast info

• Visualized results on Chicago map using Tableau

• Made recommendations for China Ofo shard bike company on Chicago market entry strategy Readmission Rate Prediction of diabetic inpatients with Machine Learning April 2018

• Built machine learning models (SVM, Decision Tree, Neutral Network) with TensorFlow on hospital readmission rate forecasting


Amateur boxer, Classtical music and Opera lover, avid reader Elaine Li


Contact this candidate