Random Forest Help

Multi-split Random Forest regression with feature importance, optional univariate screening, permutation tests and SHAP values.

Requires: One dataset with a numeric target column.

Form fields accepted by this method's POST request

analysis_type=random_forest, dataset_id, categorical_encoding, fdr_threshold, n_estimators, n_splits, permutation_repeats, random_state, run_permutation, run_shap, run_univariate, target_col, test_size

No dataset yet? Upload a file.
The variable you want to predict. Classification is auto-detected from the target column (text/categories → classification, numbers → regression).
Parameters & Options
Optional — restrict training to the selected numeric columns. Leave empty to use every numeric column. Select only columns that will also exist in datasets you plan to score with the saved model.
How non-numeric feature columns are converted before modeling.
Optional: fill missing numeric values before the analysis runs. Leave as default to keep the method's own handling.
Back to Methods