Candidate Information Name Available: Register for Free Title Data Scientist Machine Learning Target Location US-NC-Chapel Hill Email Available with paid plan Phone Available with paid plan	20,000+ Fresh Resumes Monthly     View Phone Numbers     Receive Resume E-mail Alerts     Post Jobs Free     Link your Free Jobs Page     ... and much more Register on Jobvertise Free
Search 2 million Resumes Keywords: City or Zip:	Related Resumes Data Scientist Machine Learning Durham, NC Data Analyst, Data Scientist Chapel Hill, NC Data Science Machine Learning Durham, NC Data Scientist Raleigh, NC Data Scientist Part-Time Apex, NC Associate/Consultant Data Scientist Raleigh, NC Data Analyst Machine Learning Raleigh, NC

Candidate's Name
Phone: PHONE NUMBER AVAILABLE Email: EMAIL AVAILABLE Linkedin: /in/Candidate's Name Street Address
SUMMARYData Scientist with 5+ years of experience in the Retail industry. Proficient in applying Statistical Analysis and Machine Learning modeling in Marketing and Inventory Management. Specialized in Time Series Analysis and Sales Forecasting, data-driven decision-making and optimized resource allocation. SKILLSPython, Numpy, Scipy, Pandas, Scikit-Learn, Matplotlib, Tensorflow, Keras, Deep Learning, SHAP, Seaborn, Spark, SQL, Tableau, HTML, Flask, GCP, Regression, Classification, Clustering, Time Series, Jupyter Notebook, GitHub, Linux, C/C++, Matlab, Mathematica, Analytical Models, Meta Data Analysis EXPERIENCEOld Friend Bakery Chapel Hill, NCData Scientist and Consultant 01/2023 - PresentBakery Sale PredictorTo help effectively predict the weekly bakery sales, built a Sales Forecasting Engine using time series forecasting models and classification regression models.Collaborated with sales and bakery teams to gather and analyze sales and product data. Utilized Linear Regression, Random Forest, XGBoost, and ARIMA, SARIMAX models to predict sales trends, accounting for stationarity and seasonality.XGBoost emerged as the top-performing model, achieving a test accuracy score exceeding 0.6, surpassing the benchmark by 20%. This resulted in a 40% reduction in waste and revenue increase. Additionally, provided tailored promotion suggestions for high-demand days. Techlent Inc. remoteData Scientist Fellow 06/2023 - 01/2024Drug Store Sales PredictorDeveloped a Sales Forecast Model to assist drug store managers in optimizing budget allocation based on sales demand, built sales forecasting models using time series models as ARIMA, SARIMAX, Prophet, and other regression models as Random Forest, XGBoost.Identified SARIMAX as the top-performing model to predict the daily sales with the lowest RMSE enabling actionable insights to optimize staff schedules and increase revenue potential. Achieved an RMSE below $100 per store, reducing staff costs by 30% and potentially boosting revenue by the same margin, which means the model worked well on prediction accounting all time, store types, promotions, holidays and competitions features.Deployed the SARIMAX model as a Flask API on GCP, streamlining accessibility and utilization. South China University of Technology Guangzhou, China Professor and Scientist 06/2004 - 03/2018Spam Detector on Mobile TerminalTo identify the prevalent issue of spam and scam text messages received by mobile users, an end-to-end spam detection solution was devised to improve user experience on China Mobile's communication platforms. Using regression modeling techniques, the system ranked text content based on the presence of suspicious keywords to assess the risk level. High-risk messages triggered alerts, enabling swift detection and mitigation of harmful content.The implementation of this solution significantly enhanced user satisfaction by effectively filtering out undesirable messages.Bio Products and Service Customer DetectorDeveloped a Customer Detector for Bio-Cytogen Co. to enhance sales efficiency and revenue through targeted email marketing.Collaborated with sales teams to gather historical sales data and biological/medical publications from journals and conferences. Engineered domain-specific features and trained binary classification models to identify valuable customers.Achieved 90% improvement over traditional methods, doubling revenue with existing sales investments. Interactive System for Outdoor LED Screens Development To enhance customer engagement and improve advertising effectiveness, an image optimization product was developed.This product utilizes outdoor LED cameras to capture pedestrian faces and seamlessly integrate them into advertising videos to attract the potential users to stop and watch advertisements. Customs Cigarette Anti-smuggling System TerminalDesigned and implemented a handheld terminal processing system to enable real-time query and entry of cigarette information by Customs anti-smuggling personnel. The system facilitates barcode scanning, brand comparison, origin verification, and production date entry on packaging. Additionally, it supports remote communication and warehousing functionalities. Stevens Institute of Technology Hoboken, NJVisiting Scholar 07/2014 - 07/2015Extracting Data and Layout Generation Using Web Service Lead a team to carry out the research about the project 'Extracting Data and Layout Generation Using Web Service' and get some achievements in 'Data Structure and Algorithm Analysis' and 'Advanced Database'. EDUCATIONWuhan University Wuhan, ChinaPh. D. in computer science 09/2001 - 06/2004