Kozo: Automatic Work Scheduler

  • Released iOS application that builds time management skills by automatically constructing a homework schedule
  • Managed team through a rapid 6-week development process by holding weekly debriefs and enforcing deadlines
  • Presented Kozo at the Mobile Developers of Berkeley Fall 2018 App Fair
October 2018 - Present

Viola-Jones Object Detection

  • Implemented the Viola-Jones algorithm in Python after reading the original research paper
  • Published a two-part tutorial series in The Data Driven Investor explaining the algorithm and its implementation
  • Tuned model to achieve 93% accuracy on the CBCL face database
January 2019

GoGreen: Carbon Tracker

  • Released iOS application built in Swift to track carbon footprint of a household given its monthly energy consumption
  • Using Node.JS and MySQL, designed and implemented server architecture for the application backend
  • Publicized GoGreen through social media and environmental organizations, driving 1000’s of downloads in 20 countries
  • Winner of the Congressional App Challenge 2017 for Illinois’ 10th District
June 2017 - August 2018

Machine Learning from Scratch

  • Implemented Machine Learning Algorithms from scratch in Python with no machine learning libraries
  • Derived gradient-descent for Multi-Layered Perceptron, SVM, Logistic Regression Classifier, and Linear Regression
June 2018 - August 2018

Chess AI

  • Created chess engine with textual interface written in Java with two different AI players
  • Implemented MonteCarlo Tree Search and MiniMax Search with Alpha-Beta pruning to create computer agents
July 2018

Fruit Classification

  • Designed deep convolutional neural network with Tensorflow to classify images of fruits with 92% accuracy on 40 fruits
  • Iterated upon the model design to increase the number of recognized fruits as well as accuracy
June 2018

March Madness with Machine Learning

  • Trained a Support Vector Machine on March Madness game data to create bracket for the 2017-2018 tournament
  • Ranked 75th percentile among ESPN Tournament Challenge Players and correctly predicted 27 of the first 32 games
March 2018

Physics Simulator

  • Created web app with interactive physics demonstrations with Unity to help students visualize the math behind physics
  • Managed team by dividing work, ensuring proper use of version control, and reviewing code for errors and overlap
  • Won first place at the CodeDay 2018 Chicago Hackathon
February 2018

SparkLeg IL

  • Developed website to provide understandable summaries of bills passing through the Illinois State Legislature
  • Presented at a school fair about the site to inspire students to become involved in Illinois’ political process
  • Used Node.JS and MySQL for the server backend (hosted on Heroku) and Bootstrap CSS and JQuery for the front-end
December 2017

Cube Swarm

  • Collaborated with a friend to develop an addicting mobile arcade game for iOS and Android in Unity C#
  • Engineered the mechanics of the enemies and handled iOS-specific code
June 2015 - September 2015


  • Developed scientific content aggregator to educate people through small, easily understandable pieces of information
  • Built application in iOS with Objective-C and a ASP.NET/MySQL backend
December 2014