Journal article · 2026 · Open access

A decomposable branch-and-price formulation for optimal classification trees

Elif Rana Yöner, Taghi Khaniyev, Özlem Karsu

Mathematical Programming Computation · Published 16 October 2026 · DOI 10.1007/s12532-026-00343-0

Open PDFView at the publisherCite this paper

In brief

“A decomposable branch-and-price formulation for optimal classification trees” is a 2026 journal article by Elif Rana Yöner and 2 co-authors, published in Mathematical Programming Computation. OpenAlex counts 0 citations as of 21 November 2026. It is open access under a CC BY licence: the full text is free to read at Mathematical Programming Computation.

Citations
0
References
38
Authors
3

Abstract

In this study, we focus on finding exact binary optimal classification trees (OCTs) via mixed-integer (linear) programs (MIP). To alleviate the scalability issues of existing MIP-based OCT formulations, we propose a novel decomposable model that treats each leaf of the classification tree as a decision rule. The model exploits the order-independent nature of decision rules to reduce the problem size and the solution space, and lends itself to a Dantzig–Wolfe (extended) reformulation. We then implement a tailored branch-and-price solution with pricing subproblems designated for each leaf solved in parallel. We identify the conditions under which the extended formulation performs better in order to form a hybrid algorithm, OrderIndependentOCT, that decides when to invoke branch-and-price. On 18 benchmark datasets, OrderIndependentOCT proves optimality on $$71.1\%$$ 71.1 % of instances within a one-hour time limit, compared to $$60.0\%$$ 60.0 % for the well-known Benders decomposition approach (BendersOCT). In cases where neither method attains optimality, OrderIndependentOCT yields higher (or the same) training accuracy than BendersOCT in $$50.68\%$$ 50.68 % (resp. $$71.23\%$$ 71.23 % ) of the instances. Similarly, in $$86.3\%$$ 86.3 % of all instances, OrderIndependentOCT matches or exceeds BendersOCT’s out-of-sample accuracy. These findings illustrate the efficiency of the proposed decomposition approach for the optimal classification tree training problem compared to the state-of-the-art.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Yöner, E. R., Khaniyev, T., & Karsu, Ö. (2026). A decomposable branch-and-price formulation for optimal classification trees. Mathematical Programming Computation. https://doi.org/10.1007/s12532-026-00343-0

MLA 9

Yöner, Elif Rana, et al. “A decomposable branch-and-price formulation for optimal classification trees.” Mathematical Programming Computation, 2026. https://doi.org/10.1007/s12532-026-00343-0.

Chicago

Yöner, Elif Rana, Taghi Khaniyev, and Özlem Karsu. 2026. “A decomposable branch-and-price formulation for optimal classification trees.” Mathematical Programming Computation. https://doi.org/10.1007/s12532-026-00343-0.

Harvard

Yöner, E. R., Khaniyev, T. and Karsu, Ö. (2026) ‘A decomposable branch-and-price formulation for optimal classification trees’, Mathematical Programming Computation. doi:10.1007/s12532-026-00343-0.

IEEE

E. R. Yöner, T. Khaniyev, and Ö. Karsu, “A decomposable branch-and-price formulation for optimal classification trees,” Mathematical Programming Computation, 2026, doi: 10.1007/s12532-026-00343-0.

BibTeX

@article{yoner2026decomposable,
  title     = {{A decomposable branch-and-price formulation for optimal classification trees}},
  author    = {Yöner, Elif Rana and Khaniyev, Taghi and Karsu, Özlem},
  journal   = {Mathematical Programming Computation},
  year      = {2026},
  doi       = {10.1007/s12532-026-00343-0},
  url       = {https://doi.org/10.1007/s12532-026-00343-0}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Information Systems › Data Mining Algorithms and Applications

  • binary classification tree
  • mixed-integer linear programming
  • branch-and-price
  • decomposition
  • decision rules
  • Benders decomposition
  • hybrid algorithm
  • tree training

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Yöner, E. R., Khaniyev, T., & Karsu, Ö. (2026). A decomposable branch-and-price formulation for optimal classification trees. Mathematical Programming Computation. https://doi.org/10.1007/s12532-026-00343-0

How many times has this paper been cited?

0 times, according to OpenAlex on 21 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Mathematical Programming Computation: sign in and open the PDF from this page.

Who wrote this paper?

Elif Rana Yöner, Taghi Khaniyev, Özlem Karsu.

What is the DOI of this paper?

10.1007/s12532-026-00343-0, permanently at https://doi.org/10.1007/s12532-026-00343-0. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 21 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.