Collection of my Data Science and Finance Projects
FinViz - Balance Sheet Visualizer
January 2023 - April 2023
Engineered interactive tool visualizing 10-K data using CSS, JS, and D3 library, for introductory finance class students. Implemented time-series and cross-sectional analysis with filters and tooltips to allow for comparisons across firms and years.
ReceipTrack - Receipt Image Processing
October 2022 - December 2022
Developed dashboard web app tool in team of 4 that analyzes receipt images using OCR to produce shopping habit insights. Incorporated object-oriented design and Plotly Dash to visualize spending trends over time and across food groups.
Supervised Learning in Credit Defaults
February 2023 - April 2023
Created and implemented KNN, decision tree, and logistic regression algorithms using Taiwanese credit card data from 2005, resulting in an accuracy of around 68% in predicting default. Utilized sklearn and keras libraries to train and evaluate a Random Forest and neural network models, resulting in accuracies above 70%.
Programming Language Predictor
March 2022 - April 2022
Tokenized GitHub Repository code snippets with Regex and TF-IDF to train a Multinomial Naive Bayes Classifier. Launched machine learning model on Heroku with Python framework Flask to predict programming language of user input.
Foreign Exchange Machine Learning Analysis
October 2022 - December 2022
Analyzed movement of foreign exchange currencies with Linear and Multiple Regression models using Sklearn. Explored relationship between Non-Euro, non-pegged EU nation currencies and the Euro through a Random Forest Classifier, achieving an r2 score of 0.987.
Schedule Planner - Database Software Product
October 2022 - December 2022
Developed a user-friendly application using SQL and Flask, enabling advisors and students to understand and plan academic schedules. Utilized Docker and Ngrok to connect REST Api in AppSmith to host the MVP, ensuring a functional and operational application that utilizes a schedule database.
Company Success and Executive Compensation
December 2021 - January 2022
Evaluated correlation between increase in the success of a company and the compensation for top executives with Python. Wrangled stock data for over 500 companies using Pandas library on Compustat and CRSP databases.
Financial Data and Stock Price Investigation
October 2021 - December 2021
Assembled financial data for Apple and Google over a 20 year period using Compustat and CRSP in WRDS. Quantified correlation between 10-Q ratios and stock prices in Python, researched company strategies to highlight trends.