Overview
This resume highlights Kyle Dickinson's skills, education, and experience as an aspiring quant intern with a focus on programming, machine learning, and leadership roles.
Profile & Objective
- Highly motivated high school senior proficient in Python, Pandas, and JavaScript.
- Experienced in programming and statistical modeling for quantitative finance.
- Seeks quant internship for real-world experience before starting Operations Research and Statistics at Carnegie Mellon University.
Work Experience
- Shift Leader at Dunkin since October 2023, supervising six workers per shift.
- Trained over 20 new employees on computer systems.
- Addressed employee and customer concerns with management as needed.
- Team member (June 2023 - October 2023) managing coffee/food orders and emphasizing strong customer service.
Relevant Projects and Experience
- Formula 1 Pit Stop Predictor: Built a LightGBM machine learning model to predict pit stop timing, outperforming historical baselines by 45% using Mean Squared Error.
- Data collected and cleaned via FastF1 API, managed using Pandas.
- Inspirit AI: Learned ML foundations, used Pandas in Jupyter, and designed a natural language processing algorithm for stock prediction with 86% accuracy.
- Massachusetts Science and Engineering Fair: Developed grading software leveraging color psychology and game theory to motivate students.
Education
- Incoming freshman at Carnegie Mellon University, majoring in Mathematical Science with Operations Research and Statistics concentration (Fall 2025).
- Completed AP Statistics, AP Computer Science, and AP Calculus BC.
- Mansfield High School: Co-founder of Robotics team, Varsity Track and Cross Country captain, Class President, Engineering program participant.
- Southeastern Regional Vocational Technical High School: Attended from September 2021 to October 2022.
- Louisiana State University Math Circle (July 2022): Researched subgraphs in graph theory, course instructed by Ivy League graduates.
Key Terms & Definitions
- Mean Squared Error (MSE) — A metric to measure the accuracy of a predictive model by averaging the squares of errors.
- LightGBM — A gradient boosting framework for building efficient machine learning models.
- Natural Language Processing (NLP) — Area of AI focused on the interaction between computers and human languages.
- Pandas — A Python library for data manipulation and analysis.
Action Items / Next Steps
- Apply for quant internships to gain real-world experience.
- Prepare for studies in Operations Research and Statistics at Carnegie Mellon University.
- Continue developing proficiency in machine learning and programming.