At NYC Data Science Academy, I built a shiny app to explore feature importance on small business ranking using Yelp data. I scraped all reviews for top 100 movies in 2016 and applied NLP algorithms such as TF-IDF, Topic Modeling and sentiment analysis. For the Kaggle competition, my teammates and I developed machine learning models with over 1,000 features to predict consumer interest in apartment listings using Logistic Regression, Random Forest, and XGboost. My capstone project was to make image classification in which I mainly used Neural Network and clustering, PCA, KNN to predict the author of the painting.
