Project 4: Prediction of Student's Dropout and Academic Success
-
Implemented Machine learning techniques such as Logistic Regression, Decision trees, Random forest,and K-nearest neighbors (KNN) were used to predict student dropout and academic success in a project.
-
Preprocessed the data through encoding categorical variables, dropping irrelevant columns, and splitting into training and testing sets.
-
Conducted Exploratory Data Analysis to determine the relationship between features and the target variable, and scaled the data using min-max scaling.
-
Evaluated the model performance using accuracy, precision, and recall.
-
Optimized each algorithm using GridSearchCV to reach the best model. Logistic Regression performed best after hyperparameter tuning with an accuracy of 91%.
