Figure 2
The five-step diagram is arranged from left to right in overlapping rectangular boxes, connected by right arrows. The box on the left is labeled “Step 1 Data Collection” and lists “Raw exam scores” and “Course metadata”, illustrated with a funnel icon with a pie chart shown on a paper. The second box is labeled “Step 2 Data Preprocessing” and includes “Feature Encoding” and “Feature Scaling”, shown with database and connected gear icons. The third box is labeled “Step 3 Train or Test Split” and lists “Data Train” and “Data Test”, illustrated with folder and database icons. The fourth box is labeled “Step 4 Modeling” and lists algorithms including “Logistic Regression”, “Decision Trees”, “Random Forests”, “Support Vector Machines”, “Neural Networks”, “X G Boost Regressor”, “Cat Boost”, and “Light G B M”, accompanied by a brain and circuit-style icon. The fifth box is labeled “Step 5 Evaluation” and lists “R-squared Score”, “M S E (Mean Squared Error)”, “R M S E (Root M S E)”, and “M A E (Mean Absolute Error)”, shown with a clipboard and checklist icon.Our proposal steps for predicting student cheating model