Algorithm 2: Ensemble Machine Learning Model

Step 1: Data Preparation Step 2: Base Model Training            base_models = {                   ‘Logistic Regression’: LogisticRegression(),                   ‘KNN’: KNeighborsClassifier(),                   ‘SVM’: SVC(),                   ‘Decision Tree’: DecisionTreeClassifier(),                   ‘Random Forest’: RandomForestClassifier()            } base_model_predictions = {}            for model_name, model in base_models.items():                   model.fit(X_train, y_train)                   base_model_predictions[model_name] = model.predict(X_test) Step 3: Base Model Predictions            base_model_predictions_array = np.array(list(base_model_predictions.values())).T Step 4: Meta-Model Training            meta_model = Ensemble()            meta_model.fit(base_model_predictions_array, y_test) Step 5: Final Prediction            final_predictions_array = np.array(list(base_model_predictions.values())).T            stacked_predictions = meta_model.predict(final_predictions_array) Step 6: Evaluation            accuracy = accuracy_score(y_test, stacked_predictions)            print(f”Stacking Ensemble Model Accuracy: {accuracy}”) Step 7: Explainability with LIME            def lime_explanation(model, instance, features): Step 8: Explainability with SHAP            explainer = shap.Explainer(meta_model)            shap_values = explainer.shap_values(X_test)