# Мэттьюс корреляция коэффициеті: Елу жыл

> Толық мәтін ағылшын тілінде

**Published:** 2026 ж. 9 қараша
**Author:** Jesus S. Aguilar-Ruiz
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/kk/articles/the-matthews-correlation-coefficient-fifty-years

arXiv:2611.08799v1 Хабарлама түрі: жаңа Анотация: Мэттьюс корреляция коэффициеті (MCC) енгізілгеннен кейін елу жыл өткен соң да екі sınıптеуде орталық —және даулы— қала береді. Бұл зерттеу MCC-нің кешенді ретроспективін және терең талдауын ұсынады, оның…

arXiv:2611.08799v1 Announce Type: new Abstract: Fifty years after its introduction, the Matthews Correlation Coefficient (MCC) remains central -and debated- in binary classification. This survey offers a comprehensive retrospective and an in-depth analysis of MCC, covering its historical development, mathematical foundations, and implications for practice. We clarify long-standing misconceptions, formalize its equivalences (to Pearson's correlation and to Chi2 in 2x2 tables), and examine its behavior under class imbalance. Beyond MCC, we develop analytical (derivatives) and graphical (contour plots) frameworks that generalize to any confusion-matrix-based metric. These frameworks expose structural properties -bias, robustness, sensitivity- that scalar summaries conceal, and they provide actionable guidance for selecting and interpreting performance measures in applications where reliability and fairness matter. Together, our results position MCC within a broader toolkit while clarifying when it is informative -and when alternatives may be preferable.

---

*Материал бастапқы дереккөзден алынған: [arXiv — cs.AI](https://arxiv.org/abs/2611.08799). Түпнұсқаны ашу.*

**Тегтер:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*