Predict Carbonation Depth

The SHAP Waterfall Plot provides a step-by-step explanation of how each attribute influences an individual prediction. The value E[f(x)], at the bottom of the plot, represents the model's expected prediction for the entire dataset (i.e., the average prediction). Each value in the plot shows the increase or decrease in the prediction, depending on the attribute's contribution, leading to the final prediction.

UEA - Unprotected external area
PEA - Protected external area
PIA - Protected internal area

Model Global Explainability

In the SHAP Beeswarm plot, the attributes are ordered by importance (top to bottom). Each point represents a SHAP value for a specific attribute, with points to the right of the vertical axis indicating positive contributions to the carbonation depth and to the left, negative contributions. The color gradient (red = high values, blue = low values) shows how the magnitude of the attribute affects the model's output.

beeswarm_plot_SVR
beeswarm_plot_ANN
beeswarm_plot_RF