방법 비교

	다중 팔 밴딧 (UCB, Thompson Sampling)	A/B 테스트 (온라인 통제 실험)	순차/그룹 순차 시험 설계
분야	실험설계	실험설계	실험설계
계열	Hypothesis test	Hypothesis test	Hypothesis test
기원 연도	1952	1935	1979
창시자	Robbins (1952); UCB1 by Auer et al. (2002); Thompson sampling by Thompson (1933)	Ron Kohavi et al. (Microsoft); conceptual roots in R. A. Fisher's randomized experiments (1935)	O'Brien & Fleming; Pocock; Lan & DeMets
유형	Sequential decision / bandit algorithm	Parametric comparison (frequentist or Bayesian)	Adaptive stopping trial design
원전	Auer, P., Cesa-Bianchi, N., & Fischer, P. (2002). Finite-Time Analysis of the Multiarmed Bandit Problem. Machine Learning, 47(2–3), 235–256.	Kohavi, R., Tang, D., & Xu, Y. (2020). Trustworthy Online Controlled Experiments: A Practical Guide to A/B Testing. Cambridge University Press. ISBN: 9781108724265	O'Brien, P.C. & Fleming, T.R. (1979). A Multiple Testing Procedure for Clinical Trials. Biometrics, 35(3), 549–556.
별칭	MAB, bandit algorithm, UCB1, Thompson sampling	split test, controlled experiment, two-variant test, A/B Testi (Online Kontrollü Deney)	group sequential design, adaptive stopping design, Ardışık Deneme Tasarımı (Sequential / Group Sequential)
관련	4	4	3
요약	The multi-armed bandit (MAB) is an adaptive experimental framework that allocates trials sequentially across competing arms to minimise cumulative regret while simultaneously learning which arm performs best. Formalised by Robbins in 1952 and given finite-time guarantees by Auer et al. (2002), it balances exploration of uncertain options against exploitation of currently known best options — outperforming classical A/B testing whenever early stopping or cost-sensitive allocation matters.	An A/B test is a randomized controlled experiment that simultaneously exposes two groups of users to a control variant (A) and a treatment variant (B) in order to determine whether a measured outcome differs significantly between them. The modern online controlled experiment framework was systematized by Ron Kohavi and colleagues at Microsoft in the early 2000s, building on R. A. Fisher's classical randomization principles from 1935. It is the dominant causal inference tool in web product development, digital marketing, and experimentation platforms.	Sequential and group sequential trial designs allow a study to be stopped early — or continued — based on interim analyses conducted as data accumulate. The core framework was formalised by O'Brien and Fleming in 1979 and extended by Lan and DeMets's alpha-spending approach, and it controls the overall Type I error rate across all planned looks by pre-specifying both efficacy and futility boundaries before enrolment begins.