Welcome to the 2023 Spring CMSC320 Final Project Student GPA Prediction project repository. This project focuses on utilizing advanced data science techniques to predict students' GPA based on their provided information.
The primary objective of this project is to develop and compare predictive models capable of accurately estimating a student's GPA. Leveraging a diverse set of features, we aim to deliver a robust solution that aids educational institutions in foreseeing academic outcomes.
- Algorithm Development: The heart of the project lies in crafting effective algorithms capable of transforming student information into GPA predictions.
- Model Diversity: We have implemented five distinct predictive models, each employing a different methodology to ensure comprehensive coverage and accuracy.
- Model Evaluation: Rigorous model evaluation techniques, including cross-validation and performance metrics, are utilized to assess and compare the predictive power of the models.
- Outlier Handling: A robust strategy for identifying and addressing outliers has been integrated into the modeling process, enhancing model resilience and predictive performance.
- Missing Data Handling: Implementing sophisticated imputation techniques, we tackle missing data scenarios to ensure optimal utilization of available information. One-Hot Encoding: Categorical variables are processed using one-hot encoding, enabling models to effectively interpret these variables and enhance prediction accuracy.
Contributions are highly encouraged and can be made by forking the repository, implementing enhancements, and submitting pull requests. Whether you are a seasoned data scientist or just starting, your insights and ideas are valued in advancing this project's goals.
Join us on this journey of harnessing data science to unlock insights and improve educational outcomes. Together, we strive to create a predictive model that shapes the future of student success.
Note: This repository is under active development. Please refer to the Issues section for ongoing tasks and discussions.
Download the following dataset: https://drive.google.com/file/d/14jkgeXF1_0U446EWP1Ee8L8UoJM53TYg/view?usp=sharing It contains:
- id--a student's id
- lat--student's home latittude
- lon--student's home longitude
- avg_hours_studided--how many hours this student studied every week on average this semester
- parents_income--the student's parent's income in dollars.
- major--the student's major
- tutoring--whether or not the student received tutoring this semester
- semester--what semester it is
- credits--how many credits the student took this semester
- student_age--how old the student is
- student_year--what year of college the student is
- year--what year it is