Jing Zhang

**** ******* ****** **, **********, OH 45209 (*wiling to relocate) 732-***-**** adjpe3@r.postjobfree.com LinkedIn: www.linkedin.com/in/jing-zhang9388 GitHub: https://github.com/zj88zj PROFESSIONAL SUMMARY

Statistics graduate level professional with experience in data operations/ analysis/ modeling/ visualization of consumer, clinical, business and environmental data, AI and Machine Learning algorithms, Python, SAS, R, Matlab and SQL programming. SKILLS

Technical: SAS (Base and Advanced certificates), Python (Numpy, Pandas, Matplotlib, Seaborn, Statsmodels, Pytorch), R, Matlab/Octave, SQL, JMP, JavaScript, CSS & HTML (Coursera course), Tableau (Coursera course), adv Excel.

Statistical: Data Manipulation, Regression Analysis, Multivariate Analysis, Statistical Modeling, Survival Models, Machine Learning, Data Visualization, Time Series, Forecasting

Language: Chinese (native), German (beginner)

EDUCATION

Rutgers University, New Brunswick, NJ

M.S. in Statistics GPA: 3.75 Jan 2019

M.S. in Environmental Science GPA: 3.6 Jun 2017

Relevant Courses: Introduction to AI, Regression Analysis; Biostatistics; Interpretation of Data; Applied Multivariate Analysis; Applied Time Series Analysis, Design of Experiment Tianjin University, Tianjin, China

B.S. in Environmental Science GPA: 3.2 Jun 2015

RELATED WORK EXPERIENCE

Statistician I, P&G/System One, Cincinnati, OH July 2019 - now

● Participated in designing statistical plans for clinical or consumer studies;

● Helped with data management, including data cleaning, data restructuring and data check;

● Performed data analysis, statistical modeling and data visualization, generated statistical reports;

● Mainly programed in SAS (e.g. Macro, proc SQL, ODS), alternately used R or Python for efficiency. Data Engineer Intern, Markable AI, New York, NY Jun 2018 - May 2019

● Performed data scraping with JavaScript in terminal to collect images and videos data from online sources;

● Visualized scraping taxonomy data with d3 tree and assisted the data operations team in performing data source profiling and facilitating data extraction;

● Helped with machine learning in order to identify fashion items and give related recommendations to customers, including data preparing and image classification models training with CNN in Python. SELECTED PROJECTS

Quality of Life Questionaries Analysis Internal Webtool (SAS), P&G Jan 2021

● Prepared data by data formatting, restructuring and creating new variables;

● Checked and cleaned data, conduct basic exploratory analysis;

● Performed statistical tests and additional analysis in domain/subdomain level to give insights (e.g. The trend of rating changes from baseline by time, the comparisons of responses among various products) from all customer’s responses;

● Output tables and plots for reporting purpose.

Lumi Connected System, Soft Sensor for Diaper (SAS & Python), P&G Feb 2020

● Explored rgb color data collected from the attached sensor on Lumi diaper used for tracking diaper status and baby sleep;

● Developed statistical models to analyze and visualize data in order to select best spots react to diaper status and different standards on different concentrations.

Data Preparing and Cleaning Using Image Classification with CNN (Python), Markable AI, Link Jun 2019

● Downloaded furniture images from target links, filtered and visualized images, and prepared labeled furniture data;

● Built and run image classification model with Pytorch in Python so as to identify and clean unacceptable or noise data for further model training.

Predicting Credo in J&J Research and Development Purchase Orders (R), Interpretation of Data II, Link May 2018

● Performed Exploratory Data Analysis for the dataset provided by J&J of the 907,408 purchase orders specifically in research and development area;

● Built partitions and subsets using Cluster Analysis to explore similarities and differences in the purchasing behavior within companies, businesses and suppliers in specific areas;

● Analyzed datasets with Bayesian Networks and GLMnet models to establish connections between subgroups of the data over time and emphasis in small businesses, in addition to predicting whether supervisors are likely to purchase from minority owned businesses in the 17th month.

The Analysis of Sales Data of Orthopedic Products (SAS&R), Interpretation of Data, Link Dec 2017

● Analyzed the dataset of over 4,000 hospitals in the US in order to estimate and increase potential sales of orthopedic equipment from a company to hospitals;

● Conducted factor analysis and cluster analysis for selected market segments and making data transformation, dimension reduction and variable selection;

● Adjusted regression analysis for each segment to estimate potential gain in sales and to list the hospitals in segments whose sales can be improved.

Contact this candidate