Update README.md

Author: ZRaup

README.md

@@ -143,17 +143,18 @@ This project demonstrates how domain knowledge, feature construction, and ensemb
 
 ###### Skills Applied: Machine Learning, Feature Engineering, SMOTE, SHAP, Ensemble Modeling, Supervised Learning, Python (scikit-learn, XGBoost, imbalanced-learn)
 
-#### Figure 6: Confusion Matrix — XGBoost Model
-##### This confusion matrix shows the performance of the XGBoost model in detecting machine failures. It achieved 98.6% accuracy, with only 55 total misclassifications out of 3,865 samples. The model demonstrates excellent precision and recall, making it highly effective for predictive maintenance tasks in manufacturing.
-
-<img src="ConfusionMatrix_XGBoost.png" width="400" />
-
-#### Figure 7: SHAP Summary Plot — Feature Impact on Predictions
+#### Figure 6: SHAP Summary Plot — Feature Impact on Predictions
 ##### SHAP summary plot showing how each feature influences the model’s predictions. Tool_wear_[min], Power_[W], and Rotational_speed_[rpm] are among the most influential inputs. This visualization aids in validating model behavior and supports communication with non-technical stakeholders.
 
 <img src="SHAP.png" width="500" />
 
 
+#### Figure 7: Confusion Matrix — XGBoost Model
+##### This confusion matrix shows the performance of the XGBoost model in detecting machine failures. It achieved 98.6% accuracy, with only 55 total misclassifications out of 3,865 samples. The model demonstrates excellent precision and recall, making it highly effective for predictive maintenance tasks in manufacturing.
+
+<img src="ConfusionMatrix_XGBoost.png" width="390" />
+
+
 
  &nbsp;