Since many of us competitors are in high school and are taking the SAT in the foreseeable future, we wanted to make SAT GPT to see what us students need in terms of score (using charts) to do well on the exam.
The SAT GPT code simulates a quiz resembling SAT-style questions and assesses the performance of random guessing for multiple simulations. It generates random answer choices for a set of questions, simulates random guessing of answers, records scores, and then visualizes results through various types of charts using the 'pygal' library. This project aims to explore outcomes of random guessing on SAT questions.
We built SAT GPT using Python and the 'pygal' library for chart visualization. We used data generation, which was random answer choices generated for a predetermined number of questions. We also used simulation for random guessing on each questions, scoring based on the correct and incorrect guesses, and chart visualization to visualize the simulation results.
One challenge we ran into was the randomness, and how simulating random guessing required careful handling of randomness to ensure consistent and meaningful results.
My team and I are proud of the statistical insights of the project. By calculating average scores and presenting them in various chart forms, we gained insights into the impact of random guessing on SAT-style quizzes.
In the development of this project, my group learned more about randomization. We gained a deeper understanding of randomization and its role in simulating real-world scenarios.
Log in or sign up for Devpost to join the conversation.