FathiZaireen1/Student_Scholarship_Predictor

Student Scholarship Predictor

This Space predicts whether a student is likely to receive a scholarship based on their academic and demographic profile.

Dataset

The model is trained on Student_performance_dataset.csv, which contains 6,008 student records with the following columns: StudentID, StudentName, MathScore, ScienceScore, EnglishScore, AttendancePercentage, Age, Gender, Department, and Scholarship. Rows with missing values in the columns used for training, including the single row with a missing Scholarship label, are dropped before training.

Model

Gender, Department, and Scholarship are encoded with separate LabelEncoders. The model uses MathScore, ScienceScore, EnglishScore, AttendancePercentage, Age, and the encoded Gender and Department as features to predict the encoded Scholarship status. A RandomForestClassifier (200 trees, max depth 5, minimum 10 samples per leaf, balanced class weights) is trained on an 80/20 stratified train/test split with a fixed random state of 42.

Interface

The Gradio app provides sliders for academic scores, attendance, and age, plus selectors for gender and department, and returns a Yes/No scholarship prediction with a confidence score and a full probability breakdown. The current test accuracy is displayed in the header.