End to End machine learning project

Conducted exploratory data analysis to understand the relationship between various features and student grades in specific subjects.

Preprocessed data, including cleaning, normalization, and feature engineering.

Applied machine learning algorithms, including linear regression, catboost, XGboost etc., to build models for predicting student grades.

Evaluated the performance of the models using metrics such as mean squared error and r2 squared. -Deployed the final model as a web application using Flask, allowing users to input student data and receive predicted grades.

Contributed to the full end-to-end implementation of the project, including development, testing, and deployment.