January 2020 - May 2020
For my final project in Math189R: Mathematics of Big Data, I implemented a support vector machine (SVM) model for biometric authentication of smartphone users.
March 2020 - May 2020
For my final project in Math189Z: Covid-19 Data Analytics and Machine Learning, I conducted sentiment analysis on Tweets regarding the Covid-19 pandemic using a naive Bayes classifier. Through this project, I examined the relationship between the severity of the virus and its impact on the public’s reaction to it, particularly on social media.
January 2019 - May 2019
This is an independent project I began to explore time series data. I decided to analyze stock market data, a type of time series data that is readily accessible. I built a recurrent neural network with long short-term memory (LSTM) architecture to predict changes in a company’s stock price based upon market history. I wrote code in Python and used the Tensorflow library to build the neural network. I then used the predictions of the neural network to trade stock through Alpaca, a stock brokerage, and its API. I automated the trading of the stock using Bash scripting.
June 2017 - August 2017
In the summer of 2017, I took General Assembly’s Data Science course, taught in New York City. During the course, we learned how to build machine learning algorithms – including decision trees, random forest regression and classification models, K-nearest neighbors, and logistic regression. We used Pandas and NumPy for collecting and cleaning the data, and we used Scikit-Learn for implementing the models. As part of the final project for the course, I built a random forest regression model in Python to predict the final sale prices of Iowa houses with 90% accuracy. I then presented the model’s results to General Assembly faculty and students.