melanieshi0120 Goto Github PK

• 🔭 I’m currently working @ Northwestern Mutual as a Data Engineer
• ⚡ Fun fact: I am trilingual - fluent in English 🇺🇸, Chinese 🇨🇳, and Korean 🇰🇷
• 🏋️ Workout every day!

Experience in data engineering, data analysis, and machine learning with a Data Science background. Having earned a master’s degree in Economics has provided me a solid foundation and a good intuition in Machine Learning and Statistical Analysis. My previous roles offer me excellent communication skills and a great understanding of business, consumer behavior, and strategic decision making.

• Programming & Data Visualization: Python(Scikit-learn, Pandas, Numpy, Matplotlib,Seaborn, Plotly, NLTK, SciPy, PyTorch), R, Google Analytics, Excel, Tableau, Google Data Studio

• Statistical Techniques&ML: HypothesisTesting, A/BTesting, ANOVA, Chi-squareTesting, StatisticalModeling(Linear Regression, Polynomial Regression, Ridge and Lasso Regression, Logistic Regression, Time Series), Machine Learning (KNN, Random Forest, XGBoost, Support Vector Machines, Naive Bayes, Principal Component Analysis, Clustering, Recommendation Systems), Deep Learning(Keras, TensorFlow, Neural Network-CNN, RNN, LSTM), Natural Language Processing

• Other Technical Skills: SQL, Apache Spark, Docker, Web Scraping, OOP(Object-oriented Programming), API Call, Git, GitHub

• Machine Learning for Dating Apps
• Data Science In Weight Loss Apps
• Google Anlytics for Data Science
• Why Google Cloud Platform(GCP)?
• Microeconomics and Data Science — Decision Making
• Consumer Behavior Analysis — Click the Ad or Not?
• Econometrics and Data Science

➡️ more blog posts...

• 📈Linear Regression
• 📊 Califonia_suicide_project
• Intro_GitHub_API_Data_Extraction
• 🧒🏻 👦🏻 👧🏻 PCA - Facial_Recognition
• 🧬 DNA Variation Classification
• 📉 Beijing PM2.5 Analysis - Time Series Panel Data
• NLP - Amazon Reviews- Model Stacking
• 🦠 COVID-19 - LSTM - Time Series Panel Data
• Multi-Classification - KNN/RandomForest/DecsisionTree

➡️ more projects...