Summary

Double Ph.D. in Computer Science and Mathematics with 10 years of experience overall, including 3 years of hands-on industry experience in finance developing machine learning models and data-pipelines to operate at scale. In my current role I am focused on improving price predictions and ranking comparable sales for homes across the United States. I have an extensive background in academia, which includes coursework in machine learning, deep learning, statistics, linear algebra and graph theory as well as 7 publications in the fields of robotics, discrete mathematics and statistics.

---

Career

I am currently a Senior Data Scientist at Freddie Mac working on home price estimatation models, comparable sales ranking models, housing indices and geospatial/geometric data and its applications to the housing market.

• House Price Prediction Model Enhancement:
• Created a house price prediction deep learning model which covers 100 million properties in the US. Provided a 2% accuracy boost compared to production in pre-defined testing regions
• Implemented a constant time geospatial lookup algorithm to enable enhanced data engineering
• Developed a pipeline that unified 5+ vendor data sources, improving data coverage and runtime
• Comparable Sales Model:
• Proposed and constructed tree-based appraiser adjustment models which are within 5% of the actual appraiser adjustment in 99% of the validation set
• Initiated and built a comparable sales recommendation system to generate a ranking of the best comparable sales for new construction homes. This doubled the coverage on new construction homes with an identical performance to production model
• Team Leadership and Collaboration:
• Planned and organized the 2024 Q3 hackathon to enrich the geospatial data for production models. New features provided a 1-2% boost in production price prediction models over initial testing regions
• Was selected as an officer to oversee the comparable sales model initiative]
• Won the 2023 Q1 Hackathon which involved matching school boundaries to US properties by developing the algorithm that had the best coverage and fastest runtime
• Developed automation scripts to assist new hires through the onboarding process

---

Tutoring

I am currently offering tutoring services for a variety of subjects in both mathematics and computer science. These subjects include, but are not limited to:

• ACT and SAT math section preparation
• GRE quantitative section preparation
• Algebra
• Trigonometry
• Calculus
• Differential Equations
• Linear Algebra
• Complex Analysis
• Probability and Statistics
• Discrete Mathematics
• Python
• Data Structures and Algorithms
• Data Science
• Machine Learning
• Artifial Intelligence
• Deep Learning

Please email me if you would like to chat about setting up tutoring!

---

Ph.D. in Computer Science

August 2019 - January 2022

I completed my Ph.D. at the University of South Carolina in the Department of Computer Science and Engineering. Jason O'Kane advised me in discovering more about Visibility-Based Multi-Robot Pursuit-Evasion problems, including innovative sampling ideas and robustness.

---

Ph.D. in Mathematics

August 2016 - May 2020

I earned a Ph.D. from the University of South Carolina in the Department of Mathematics. Éva Czabarka and László Székely co-advised me in exploring graph invariants in triangulations and quadrangulations of the sphere.

---

Other Education

August 2009 - May 2021

• M.S. Computer Science (2021) - University of South Carolina
• M.A. Mathematics (2015) - University of Miami
• B.S. Computer Science and Mathematics (2013) - Palm Beach Atlantic University
• Associate of Arts (2011) - Inver Hills Community College

Computer Science

1. Robust-by-Design Plans for Multi-Robot Pursuit-Evasion (accepted, ICRA 2022)
2. Rapid Recovery from Robot Failures in Multi-Robot Visibility-Based Pursuit-Evasion (accepted, IROS 2021)
3. A Visibility Roadmap Sampling Approach for a Multi-Robot Visibility-Based Pursuit-Evasion Problem (accepted, ICRA 2021)

---

Mathematics (Authors are typically ordered alphabetically)

1. Minimum Wiener Index of Triangulations and Quadrangulations (accepted, Discrete Applied Mathematics)
2. Proximity in Triangulations and Quadrangulations (accepted, Electronic Journal of Graph Theory and Applications)
3. Wiener Index and Remoteness in Triangulations and Quadrangulations (accepted, Discrete Mathematics & Theoretical Computer Science)

---

Miscellaneous

1. Clinical Characteristics of Suspected COVID-19 in Pediatric Patients (accepted, International Journal of Critical Care and Emergency Medicine)

---

In Preparation

1. Increasing Nicotine Dependence Treatment Encounters Through Nursing Education
2. Sampling in Multi-Robot Pursuit Evasion
3. Robustness in Multi-Robot Pursuit Evasion
4. Minimum Complexity in Triangulations and Quadrangulations

Python Programming

• 100 Days of Code: The Complete Python Pro Bootcamp for 2022 teaches Python from the ground up and covers a lot of interesting concepts in an easy to follow format.
• OnlineGDB allows you to run Python code without any installation.
• Advent of Code provides programming challenges with some personality.
• Project Euler challenges both your programming and mathematical abilities.
• LeetCode contains a massive amount of exercises closely related to technical coding interviews.

Data Science and Machine Learning

• Complete A.I. & Machine Learning, Data Science Bootcamp teaches essential data science and machine learning skills in a repitious way that makes the lessons stick. I prefer PyTorch to Tensorflow, so skip the Tensorflow portion of this course for the bullet point below.
• PyTorch for Deep Learning teaches the essentials of deep learning using PyTorch. Note you should work through the course above prior to diving into this course. A free sample can be found here.
• Kaggle has thousands of datasets as well as forums and posted solutions. This can be utilized for nearly every type of data science project.
• Stat Quest presents a wide range of topics in an enjoyable and understandable way.
• The Hundred-Page Machine Learning Book concisely covers a lot of essential topics in machine learning. The author also has an expanded follow up book Machine Learning Engineering.
• Deep Learning: A Visual Approach illustrates a bunch of topics from machine and deep learning.