Ignore some weak “Folds” for Cross-validation.

Calculate and compare accuracy, before using each “Fold”.

Cross-validation (Image by Author)

Ignore some weak Folds

Ignore some weak Folds (Image by Author)
Overfitting (Sofa Designer: Fabio Novembre)

Another evaluation for selecting weak Folds

Once again, training with all the dataset

Can changing the value of “random_state” improve our score?

Senior Civil Structural Engineer, Kaggle Master, Researcher, Developer. https://www.soliset.com, https://www.farsi.media, https://www.newchains.info