Decision trees: from efficient prediction to responsible AI

Hendrik Blockeel; Laurens Devos; Benoît Frénay; Géraldin Nanfack; Siegfried Nijssen

doi:10.3389/frai.2023.1124553

Decision trees: from efficient prediction to responsible AI

Hendrik Blockeel, Laurens Devos, Benoît Frénay, Géraldin Nanfack, Siegfried Nijssen

Research output: Contribution to journal › Review article › peer-review

82 Downloads (Pure)

Abstract

This article provides a birds-eye view on the role of decision trees in machine learning and data science over roughly four decades. It sketches the evolution of decision tree research over the years, describes the broader context in which the research is situated, and summarizes strengths and weaknesses of decision trees in this context. The main goal of the article is to clarify the broad relevance to machine learning and artificial intelligence, both practical and theoretical, that decision trees still have today.

Original language	English
Article number	1124553
Journal	Frontiers in Artificial Intelligence
Volume	6
DOIs	https://doi.org/10.3389/frai.2023.1124553
Publication status	Published - 2023

Funding

This work was supported by the Research Foundation–Flanders and the Fonds de la Recherche Scientifique–FNRS under EOS No. 30992574 (VeriLearn) and by the Flemish Government (AI Research Program).

Funders	Funder number
Fonds de la Recherche Scientifique F.R.S.-FNRS	30992574
Fonds Wetenschappelijk Onderzoek
Vlaamse regering

Keywords

combinatorial optimization
decision trees
ensembles
explainable AI
learning under constraints
machine learning
responsible AI

Access to Document

10.3389/frai.2023.1124553

frai-06-1124553Final published version, 528 KBLicence: CC BY

Cite this

@article{c7f6dd220cb4414ebbc349f196e35eab,

title = "Decision trees: from efficient prediction to responsible AI",

abstract = "This article provides a birds-eye view on the role of decision trees in machine learning and data science over roughly four decades. It sketches the evolution of decision tree research over the years, describes the broader context in which the research is situated, and summarizes strengths and weaknesses of decision trees in this context. The main goal of the article is to clarify the broad relevance to machine learning and artificial intelligence, both practical and theoretical, that decision trees still have today.",

keywords = "combinatorial optimization, decision trees, ensembles, explainable AI, learning under constraints, machine learning, responsible AI",

author = "Hendrik Blockeel and Laurens Devos and Beno{\^i}t Fr{\'e}nay and G{\'e}raldin Nanfack and Siegfried Nijssen",

note = "Publisher Copyright: Copyright {\textcopyright} 2023 Blockeel, Devos, Fr{\'e}nay, Nanfack and Nijssen.",

year = "2023",

doi = "10.3389/frai.2023.1124553",

language = "English",

volume = "6",

journal = "Frontiers in Artificial Intelligence",

issn = "2624-8212",

publisher = "Frontiers Media SA",

}

TY - JOUR

T1 - Decision trees

T2 - from efficient prediction to responsible AI

AU - Blockeel, Hendrik

AU - Devos, Laurens

AU - Frénay, Benoît

AU - Nanfack, Géraldin

AU - Nijssen, Siegfried

PY - 2023

Y1 - 2023

N2 - This article provides a birds-eye view on the role of decision trees in machine learning and data science over roughly four decades. It sketches the evolution of decision tree research over the years, describes the broader context in which the research is situated, and summarizes strengths and weaknesses of decision trees in this context. The main goal of the article is to clarify the broad relevance to machine learning and artificial intelligence, both practical and theoretical, that decision trees still have today.

AB - This article provides a birds-eye view on the role of decision trees in machine learning and data science over roughly four decades. It sketches the evolution of decision tree research over the years, describes the broader context in which the research is situated, and summarizes strengths and weaknesses of decision trees in this context. The main goal of the article is to clarify the broad relevance to machine learning and artificial intelligence, both practical and theoretical, that decision trees still have today.

KW - combinatorial optimization

KW - decision trees

KW - ensembles

KW - explainable AI

KW - learning under constraints

KW - machine learning

KW - responsible AI

UR - https://www.scopus.com/pages/publications/85167445769

U2 - 10.3389/frai.2023.1124553

DO - 10.3389/frai.2023.1124553

M3 - Review article

AN - SCOPUS:85167445769

SN - 2624-8212

VL - 6

JO - Frontiers in Artificial Intelligence

JF - Frontiers in Artificial Intelligence

M1 - 1124553

ER -

Decision trees: from efficient prediction to responsible AI

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this