IBLM1.0.2 package

Interpretable Boosted Linear Models

beta_corrected_density

Density Plot of Beta Corrections for a Variable

beta_corrected_scatter

Scatter Plot of Beta Corrections for a Variable

beta_corrections_derive

Compute Beta Corrections based on SHAP values

bias_density

Density Plot of Bias Corrections from SHAP values

check_data_variability

Check Data Variability for Modeling

check_iblm_model

Check Object of Class iblm

correction_corridor

Plot GLM vs IBLM Predictions with Different Corridors

create_beta_corrected_density

Create Pre-Configured Beta Corrected Density Plot Function

create_beta_corrected_scatter

Create Pre-Configured Beta Corrected Scatter Plot Function

create_bias_density

Create Pre-Configured Bias Density Plot Function

create_overall_correction

Create Pre-Configured Overall Correction Plot Function

data_beta_coeff_booster

Obtain Booster Model Beta Corrections for tabular data

data_beta_coeff_glm

Obtain GLM Beta Coefficients for tabular data

data_to_onehot

Convert Data Frame to Wide One-Hot Encoded Format

explain_iblm

Explain GLM Model Predictions Using SHAP Values

extract_booster_shap

Extract SHAP values from an xgboost Booster model

get_pinball_scores

Calculate Pinball Scores for IBLM and Additional Models

load_freMTPL2freq

Load French Motor Third-Party Liability Frequency Dataset

overall_correction

Plot Overall Corrections from Booster Component

predict.iblm

Predict Method for IBLM

shap_to_onehot

Convert Shap values to Wide One-Hot Encoded Format

split_into_train_validate_test

Split Dataframe into: 'train', 'validate', 'test'

theme_iblm

Custom ggplot2 Theme for IBLM

train_iblm_xgb

Train IBLM Model on XGBoost

train_xgb_as_per_iblm

Train XGBoost Model Using the IBLM Model Parameters

Implements Interpretable Boosted Linear Models (IBLMs). These combine a conventional generalized linear model (GLM) with a machine learning component, such as XGBoost. The package also provides tools within for explaining and analyzing these models. For more details see Gawlowski and Wang (2025) <https://ifoa-adswp.github.io/IBLM/reference/figures/iblm_paper.pdf>.

  • Maintainer: Karol Gawlowski
  • License: MIT + file LICENSE
  • Last published: 2025-12-16