I face a problem with using SHAP value to interpret the Tree-based model.
First, I have input around 30 features and I have 2 features that have high positive correlation between them.
After that, I train the XGBoost model(python) and look at SHAP values of 2 features the SHAP values have negative correlation.
Could you all explain to me, why the output SHAP values between 2 features don't have the correlation the same as input correlation? and I can trust that output of SHAP or not?
The correlation between input: 0.91788
The correlation between SHAP values: -0.661088
2 features are
1) Pupulation in province and
2) Number of family in province.
Train AUC: 0.73
Test AUC: 0.71