About Me

Hello, my name is Ellise Parnoff! I am a Master of Science in Data Science student at Columbia University’s Fu Foundation School of Engineering and Applied Science. In 2023, I graduated from Fordham University, where I maintained a GPA of 3.7, studying Mathematics and Computer Science.

My career goal is to use data science for good. I seek to do this by utilizing my knowledge of mathematics and programming through data science to improve social justice issues. I gained experience with this last summer when I had the opportunity to assess gender and racial bias in graduate school letters of recommendation using machine learning and natural language processing.

One of my biggest strengths is my ability to communicate my technical knowledge. Through my time working at the National Museum of Mathematics, I gained thorough experience communicating multiple advanced math concepts to a wide range of museum-goers.

Above all, I am a highly passionate hard worker who brings 110% to every task. I am eager to put my passion for STEM to work.

My skills include but are not limited to Python, R, SQL, C++, Machine Learning, NLP, Experimentation, Predictive Modeling, Data Analysis, Jupyter Notebooks, GitHub, Google Colab, Linux, Written and Verbal Communication.

Feel free to contact me with any inquiries or requests! I'd be happy to chat!

Research Interests: Astronomy, social justice

Research

Publications:

Parnoff, E., Raghuram, A. Ramanujan's congruence primes. Involve, a Journal of Mathematics. 2023.

  • For this project, I worked to find new instances of special prime numbers named Ramanujan Congruence Primes. I designed Python programs to compute multiple advanced mathematical formulas. Through our research, we have proven that it is possible to find additional Ramanujan Congruence Primes. In addition to the publication, I presented our findings at the Hudson River Undergraduate Math Conference in Massachusetts.
  • Watch my conference presentation here!

Zhao, Y., Wang, T., Mensah, D., Parnoff, E., He, S., Weiss, G. A Quantitative Machine Learning Approach to Evaluating Letters of Recommendation. HICSS-57. 2023.

  • For this project, I created and optimized predictive models using NLP and machine learning to assess and improve evaluation methods for graduate letters of recommendation. Our work has since been published in the Hawaii International Conference on System Sciences ‘24.

    • Experience

    Data Science Research Intern at GE Aerospace Research (June 2024 — December 2024):

    • Contributed to high-priority project efforts as part of the AI/Computer Vision research team
    • Implemented a Kalman Filter in C++ to improve data processing for a critical project, enhancing the overall system accuracy
    • Developed a Python script to automate 2D COCO dataset creation from 3D CT scan volumes for training
    • Collaborated closely with research team to ensure seamless communication and integration of findings

    Research Assistant Fellow at Fordham University (June 2022 — June 2023):

    • Created and optimized predictive models using NLP and machine learning to assess and improve evaluation methods for graduate letters of recommendation
    • Completed 300+ hours extracting, preprocessing, and analyzing a dataset with over 4000 entries
    • Collaboratively published a research paper for the Hawaii International Conference on System Sciences ‘24
    • Maintained strong virtual communication with a research team of two professors and two students

    ROOT Program Participant at the National Museum of Mathematics (May 2022 — August 2022):

    • Achieved selection to the highly competitive 2022 ROOT (Real Operational Outreach Training) Program
    • Communicated advanced ideas to diverse audiences (ages ranging from 2-80 with various backgrounds)
    • Engaged with high-profile mathematicians to gain a deeper understanding of advanced math concepts
    • Collaborated to enhance the accessibility of math education within the local community

    Calculus Grader at Fordham University (September 2022 — Present):

    • Assess and grade assignments on a weekly basis for two calculus classes, each with 30 students
    • Analyze and evaluate various written math solutions to determine accuracy
    • Collaborate with professor to discuss class progress and make recommendations
    • Gain a deeper understanding of fundamental math concepts