Project Workflow~
- Data Preprocessing:
o Handled missing values through appropriate imputation techniques.
o Transformed categorical variables using Label Encoder.
o Scaled numerical features for better model performance.
- Exploratory Data Analysis:
o Visualized the relationships between features and the loan status.
o Analyzed distribution patterns of key attributes like income, loan amount, and credit history.
- Model Building:
o Implemented various machine learning algorithms including:
• Logistic Regression
• Random Forest
• Support Vector Machine (SVM)
• KNeighborsClassifier
o Performed hyperparameter tuning to optimize model performance.
- Model Evaluation:
o Evaluated models using accuracy_score
- Final Model:
o Selected the best-performing model based on evaluation metrics.
o Provided insights on feature importance to understand the key factors influencing loan approval.
Results~
• The final model achieved an accuracy of 78%
• The most influential features in predicting loan status included credit history, applicant’s income, and loan amount.