About Me
Background
I am currently pursuing a B.S. in Computer Science at the University of Michigan. Here, I have completed rigorous corsework in a variety of subjects including computer science, statistics, mathematics, economics, and others. Currently, I am continuing my studies while working part-time as Data Engineer at Lineage Logistics.
Intrests
I am deeply interested in exploring the capabilities and limits of machine learning. My interest in this field led me to build a machine learning model to predict fantasy football points this past summer and a model to predict the median income of counties in the United States. In the future, I plan to improve both of these models.
Skills
Throughout my coursework, I have gained experience in a variety languages including C++, Python, R, and LaTeX. In addition to these, I am proficient in HTML and CSS (this website was built with Matrial Design for Bootstrap CSS). I am also currently learning SQL, and I will be gaining experience in C, Assembly, and Javascript(React) this fall.
Education
University of Michigan: 2020 - Present
In the Spring of 2024, I will be graduating from the University of Michigan with a degree in Computer Science as well as a minor in Applied Statistics. Currently, I am a member of one student organization, the Michigan Football Analytics Society where I have been able to discuss ideas pertaining to the application of statistics and machine learning towards american football and write an article on a machine learning model I created to predict fantasy football points. As of the Summer of 2022, I have taken a number of courses computer science, statistics, mathematics, economics, and other subjects. Some relevant courses that I have taken and those that I will be taking in the future are displayed below. Additionally, courses that I will be taking in the Fall of 2022 are listed below.
Relevant Courses- Data Structures and Algorithms (EECS 281): This course covered data structures in C++, algorithms (sorting, searching, graph, etc.), algorithm analysis, and optimization in C++.
- Programming and Introductory Data Structures (EECS 280): This course covered various datatypes (arrays, vectors, c-strings, and strings), pointers, and object-oriented programming all in C++.
- Applied Statistical Methods II (STATS 401): This course covered modeling and analysis of data with multiple linear regression (including diagnostics and model selection, two-way analysis of variance, interactions, transformations, and multiple comparison) in R.
- Foundations of Computer Science (EECS 376): This course covered topics in Theoretical Computer Science such as automata theory, decidable and undecidable problems, polynomial time computability and paradigms of algorithm design, computation complexity theory, coping with intractability, exploiting intractability, and cryptography.
- Other relevant courses include Discrete Math (EECS 203), Introduction to Statistics and Data Analysis (STATS 250), and Elementary Programming Concepts (EECS 183).
- Web Systems (EECS 485): This course will cover client/server protocols, security, information retrieval and search engines, scalable data processing, and fault tolerant systems, and will incorporate a variety of languages including Python (Flask), Javascript (React), SQLite, and more.
- Introduction to Computer Organization (EECS 370): This course will cover the basic concepts of computer organization and hardware, and will be taught in C and an assembly language.
- Introduction to Statistical Computing (STATS 306): This course will cover concepts in computer programming and statistical computing techniques as they are applied to data extraction and manipulation, statistical processing and visualization in R.
Detroit Catholic Central High School 2016 - 2020
Throughout high school, I was a member of several student organizations including the Finance Club where as a member of the club, I was able to help manage a portfolio worth nearly 100 thousand dollars. I also was a member of football team through all four years, and I was a member of DECA where I competed in the Stock Market Challange. I was part of the National Honors Society from 2018 to 2020, and I completed five Advanced Placement classes (Statistics, Calculus AB, Spanish, U.S. History, and U.S. Government and Politics).
Experience
- Using Python and Snowpark, develop routines utilizing machine learning and statistics to quantify data quality in multiple datasets over one million rows.
- Research various approaches, algorithms, and Python libraries related to anomaly detection.
- Built a web application for data profiling to provide technology teams with a tool for data analysis and visualization.
- Constructed a clustering algorithm from scratch that leveraged natural language processing and geospatial data to make predictions on over 400 thousand rows of data.
- Wrote routines to clean and geocode hundreds of thousands of rows of data using Python and Snowflake.
- Applied Machine Learning and Statistical Analysis techniques to football data.
- Improved technical skills in Python and R.
- Individually, created a machine learning model to predict fantasy football stats (located on GitHub).
- Communicated advantages and disadvantages of shoes to customers.
- Ensured that the correct quantities of shoes were delivered.
- Tracked quantities of shoes for customers in an inventory management system.
Projects
Fantasy Football Web Application and Model
Independently, I built a Fantasy Football Machine Learning model with many improvements from my previous attempt, along with a web application for displaying these predictions in tabular and graphical formats. The project is entirely written in Python. The application is built with Streamlit and uses AG Grid and Plotly. The model is comprised of multiple XGBoost Classifier models.
Model Code Application Code Application
County Median Income Multiple Regression Model
This model was created as part of a course project for STATS 401. In this project, I constructed a multiple regression model to predict median income at the county level. The full code repository is available on my GitHub repository (link to GitHub is in the contact section), but the report and appendices is available below.
Report Appendices Code Repository
Projects From EECS 281
Per class sylabus, I am not allowed to post these projects online. However, in this course I completed a number of projects including a map-searching algorithm, a Star Wars battlefield simulator, implementations of various types of priority queues, a SQL inspired database, and implementations of graph algorithms (Exact and approximate Traveling Salesman Problem algorithms and a Minimum Spanning Tree Algorithm). These projects were all completed in C++, and a large emphasis was placed on time and memory optimization.
Projects From EECS 280
Per class sylabus, I am not allowed to post these projects online. However, in this course I completed a number of projects including a statistical analysis tool, an image processing program, a Euchre Card Game, a linked-list implementation, and a machine learning algorithm (Bayesian Logistical Regression). Additionally, all of these projects were implemented in C++.
Fantasy Football Points Prediciton Model
This project was originally created to predict fantasy Football points for the 2021 - 2022 NFL season, but I plan to improve this model for the 2022 - 2023 season. In this project, I leveraged a number of Python libraries to help accomplish my goals including scikit-learn, pandas, beautifulsoup, and urllib.
In-Depth Summary Code Repository
Personal Website
This website was originally created in the Spring of 2021. Since then, I have continued to update and improve the functionality and design of this site. Most recently, I completed a total overhaul of the site, in which I redesigned it and developed it using HTML and MD Bootstrap.