SHapley Additive exPlanations

To enhance the interpretability of machine learning model predictions, we employed the SHAP analysis method. SHAP assigns a Shapley value to each feature, where the positive or negative nature of the value reflects the feature’s positive or negative contribution to the prediction results. This approach provides users with a more comprehensive understanding of the model’s decision-making process and the impact of each feature on the overall performance.

For a more intuitive presentation of the SHAP analysis results, we utilized the Beeswarm plot. These visualizations effectively showcase the SHAP values assigned to each feature, emphasizing their significance in predicting outcomes and facilitating the interpretation of the model’s behavior.