Haoxi Huang

347-***-**** acwrtj@r.postjobfree.com

EDUCATION

FORDHAM UNIVERSITY, GABELLI SCHOOL OF BUSINESS, New York, NY 2015-present MS, Business Analytics, Expected December 2016, GPA 3.71 Related Courses: Database Management – IBM (Data Studio, InfoSphere Data Architect, DB2) & SQL; Data Mining – IBM® SPSS Statistics; Text Analytics – Python, NLTK package, Weka, IBM SPSS Text Statistics; Web Analytics – Python, TwitterAPI, Stanford Parser; Explanatory Models – R studio; Big Data Analytics – Hadoop/Hive, Spark; Business Modeling Spreadsheets – MS Excel, VBA, LP solver, Monte Carlo Simulation SOUTH EAST UNIVERSITY, Nanjing, China 2010-2014

BA in Mathematics and Applied Mathematics, GPA 3.0 PROFESSIONAL EXPERIENCE

myKlovr, New York

Data Scientist Intern 9/16 – present

Modeled student performance by quantified the weighted features of their academic, professional and personal behaviors

Researched how to evaluate the quality of student performance models using supervised machine learning methods

Implemented a job recommender based on students’ profile and job posting using NLP and vector similarity techniques Fordham University, New York

Graduate Research Assistant 2/16 – present

Trained intensively in data science problem-solving approaches common in industry

Built the personalized recommendation system for a Chinese mobile application online platform named XYZS based on the user web traffic and click through data scrapped from the platform’s server

Implemented 8 different mobile apps ranking algorithms into the cleaned dataset and evaluated their qualities

Created the feature dictionary for users and mobile apps and identified the key features that would increase the web traffic Graduate Teaching Assistant for Text Analytics, Web Analytics 2/16 – present

Created 3 new lab tutorials concerning NLTK Python package for Text Analytics

Developed the Python programming code and tutorials for lab session

Taught 12 different labs for Text Analytics and Web Analytics classes

Performed academic tutoring and grade course-related assignments and projects New York City Department of Design and Construction, New York Data Analyst Intern 1/16 – 9/16

Used Python Pandas scripts to cleaned the 16000 messy raw data into a structured form appropriate machine learning

Built the statistical prediction model for DDC change order budget and delivered the project as a web app using Flask

Consulted with client on a weekly basis to discuss work plan and provide status report BUSNIESS ANALYTICS PROJECTS

Mobile Apps text content clustering for the Itunes App Store Spring 2016

Scraped all the information of all the popular mobile apps from Itunes App store using Python BeautifulSoup

Utilized the k-means clustering algorithm to cluster descriptions and customer reviews of all the popular mobile apps March Data Crunch Madness Sponsored by Deloitte Spring 2016

Predicted winning probability of each team by using data mining techniques in Python with accuracy of 73%

Cleaned historical dataset by using R programming Fans Motivation Analysis for the Brooklyn Nets Basketball Fall 2015

Scraped around 30,000 tweets and all the related twitter account information about Brooklyn Nets Basketball

Modeled social relations of twitter accounts and implemented sentiment analysis of all the tweets using AlchemyAPI TECHNICAL SKILLS

Programming: Expert in Python and related data analysis packages like Numpy, Pandas, Matplotlib, Seaborn, BeautifulSoup, Scrapy, NLTK, Sklearn. Proficient in R programming, Hadoop, Spark and SQL. Software: EXCEL, Tableau, Spotfire, Qlikview, Weka, IBM Cognos, Alteryx