A tree-based varying coefficient model

Henning Zakrisson, Mathias Lindholm
1/11/2024
stat.MLcs.LG

No official code found. Best implementation: henningzakrisson/local-glm-boost (4 stars, MIT, last commit 2024-08-23).

Abstract

The paper introduces a tree-based varying coefficient model (VCM) where the varying coefficients are modelled using the cyclic gradient boosting machine (CGBM) from Delong et al. (2023). Modelling the coefficient functions using a CGBM allows for dimension-wise early stopping and feature importance scores. The dimension-wise early stopping not only reduces the risk of dimension-specific overfitting, but also reveals differences in model complexity across dimensions. The use of feature importance scores allows for simple feature selection and easy model interpretation. The model is evaluated on the same simulated and real data examples as those used in Richman and Wüthrich (2023), and the results show that it produces results in terms of out of sample loss that are comparable to those of their neural network-based VCM called LocalGLMnet.

View on arXivView PDF

Code Implementations(1)

henningzakrisson/local-glm-boostCommunity100%
MIT

Python package that implements the LocalGLMBoost algorithm for explainable machine learning regression.

42R, PythonJun 30, 20232 years agoMIT

Similar Papers

Bayesian Data Sketching for Varying Coefficient Regression Models

78% match2025

Explainable AI for Trees: From Local Explanations to Global Understanding

77% match1 repo1982019

Comparing Model-agnostic Feature Selection Methods through Relative Efficiency

77% match2025

The Impact of Feature Scaling In Machine Learning: Effects on Regression and Classification Tasks

77% match2025

From Point to probabilistic gradient boosting for claim frequency and severity prediction

77% match2024

Learning concise representations for regression by evolving networks of trees

76% match1 repo382018

Cite this paper

@article{zakrisson2024treebased,
  title  = {A tree-based varying coefficient model},
  author = {Henning Zakrisson and Mathias Lindholm},
  year   = {2024},
  eprint = {2401.05982},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2401.05982v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2401.05982.svg)](https://codeofpaper.com/paper/2401.05982)

Discussion