Description

This project studies how different factors affect students’ test scores in math, reading, and writing. Using data from 1,000 students, it looks at how gender, ethnicity, parental education, lunch type, and test preparation influence performance.
Machine learning models (like linear and ridge regression) were used to predict scores, reaching about 88% accuracy.
The results show that gender, family background, and study preparation have a strong impact on student achievement.
These insights can help schools design better learning support and reduce performance gaps.