Yang Jie Email & Phone Number

Chapel Hill, North Carolina, United States

Bakery 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 0.87, surpassing the random-selection benchmark by 20%. This provided tailored production schedule for the high-demand days and resulted in a 40% cost decrease and revenue increase.Skills:Python, NumPy, Scipy, Pandas, Matplotlib, Seaborn, Scikit-Learn, SQL, PCA, ARIMA, SARIMA, SVM, SHAP,GitHub, Flask, Beautiful Soup, Selenium, TensorFlow, Keras, PyTorch, CNN, RNN, LSTM, NLTK, NaturalLanguage Processing (NLP), Large Language Models (LLMs), Generative AI, AWS, Microsoft Azure, Google CloudPlatform (GCP), Snowflake, Databricks, Hadoop, Spark, Tableau, Power BI, A/B Testing, Dataiku, MATLAB, VBA

Great Triangle, Nc Area

To assist drug store managers in optimizing budget allocation based on sales demand, developed a Sales Forecast Model using time series models as ARIMA, SARIMAX, Prophet, and other regression models as Random Forest, XGBoost.Collaborated with stakeholders to obtain and analyze the sale and store data sets. Identified ARIMAX as the top-performing model to predict the daily sales with the lowest RMSE. Reduced staff costs by 30% and boosted revenue 30% accordingly by the same margin.Deployed the SARIMAX model as a Flask API on GCP, streamlining accessibility and utilization.

Spam Detector on Mobile TerminalTo identify the prevalent issue of spam and scam text messages received by mobile users, devised an end-to-end spam detection model.Collaborated with user managers and text database managers, built a regression model to rank text content based on the presence of suspicious keywords to assess the risk level. The model resulted in High-risk messages alerts enabling swift detection and mitigation of harmful content. Decreased 40% spam and scam messages compared to random-check benchmark. Bio products and service Customer DetectorTo enhance sales efficiency and revenue through targeted email marketing, developed a Customer Detector for Bio-Cytogen Co. 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.

Extracting Data and Layout Generation Using Web ServiceLead 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'.

Ph. D., Computer Science- Formal Method

Activities and Societies: KEY LAB OF NATIONAL SOGTWARE ENGINEERINGPHD

Visiting Scholar, Computer Science

Activities and Societies: lecture, international conference attendance, research in Data Security group

Master Of Engineering - Meng, Computer Science

Bachelor'S Degree, Computer Science