Sales Data

Linghui (Karina) Zeng

Ireland Street, Queens, Ny 11373 518-***-**** *******.******.****@*****.***

Working Experience

Data Scientist Havi Global Solutions 2015JUN-2018FEB

Built machine learning process with regression (linear, gbrt, time series), classification algorithms

(decision tree, random forest, svm, naive bayes), clustering analysis (k-means, mean shift, Agglomerative, DBSCAN, GaussianMixture) for sales forecast, products substitution/proxy analysis and promotion analysis with python sklearn, statsmodels, lightgbm packages.

Data engineering included missing values, annoying values, outliers, normalization, feature scaling, data frame transportation, data type conversion with python pandas and numpy packages.

Data analysis including schedule batch programs, aggregation, seasonality and trend analysis, forecast indices analysis, abnormal data analysis, descriptive analysis etc.

Crawled external data from the web to support analysis moving forward more smoothly and accurately.

Researched and developed of recommendation system by optimization algorithm and genetic algorithm.

Created UI in a linux server to display historical sales data, statistic indices, and forecast data with R Shiny. Allowed users to reach live data in various database, to generate multiple types of graphs and to download data & graphs. Integrated UI with google analytics for user behavior analysis. Data Analyst Intern Meilele 2014JUN-2014AUG

Built a prototype of collaborative filtering recommendation system for e-commercial advertise recommendation.

Made a/b test online with hypothesis test for layout or content change on shopping website with traced data from google analysis tools and backend database.

Optimized offline stores products display based on product sales.

Analyzed online cart recommendation performance, customers behavior tracking indices, and customer transforming rate to customers classification based on city differentiation with R. Technical skills

Machine Learning: Regression, Classification, Clustering, NLP, Recommendation System, Time Series, DNN Analysis tools: R, Python, SQL, Google Analysis, Azure, AWS Db & Os Tools: Oracle, My SQL, Postgres, Windows, Mac, Linux, Unix Other Tools: R Shiny, Tableau, Jira, Bitbucket, Github, TensorFlow, nltk Education

Master of Science in Analytics 2018-2020 Harrisburg University Harrisburg PA Master of Science in Business Analytics 2013-2014 Rensselaer Polytechnic Institute Troy NY Bachelor of Business Administration 2008-2012 Jiangnan University Jiangsu China Project experience

Regression --- Lawn and Garden Battery Sales Prediction Kaggle House Prices (top 54%) Kaggle Grocery Sales Forecasting

Recommendation --- Netflix Recommendation Competition Google Analytics --- Vital Vio Company Marketing Research Classification --- Kaggle Titanic (top 37%) NYC Coffee Store Location Prediction NLP --- Kaggle Movie Review Sentiment Analysis