Stochastic Decision Support under Uncertainty: Markov Transitions and Monte Carlo Simulation
Qubahan Educational Journal · 01.10.2026 · 3 (4) · 1-16
DOI: 10.48161/qej.v3n4a22 ↗Kurz gefasst
Fachartikel in der Zeitschrift Qubahan Educational Journal, online erschienen am 01.10.2026. Verfasst von Maryna Shlenova und 1 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
This study develops and evaluates a stochastic-process modeling framework for decision support under uncertainty. Random processes in operational systems evolve over time, yet many decision-support procedures still rely on deterministic summaries that do not show transition risk, future-state uncertainty, or the probability of adverse outcomes. The proposed framework integrates probability distribution fitting, Markov state-transition modeling, and Monte Carlo simulation to convert uncertain system behavior into measurable decision indicators. We use two empirical cases: hourly traffic-flow data with 48,120 observations from four junctions and a predictive-maintenance dataset with 10,000 machine-operation observations. In the traffic case, we transform vehicle counts into low, moderate, high, and critical congestion states and estimate transition matrices to model next-hour movement between states. In the maintenance case, operating variables are converted into normal, watch, high-risk, and failure states to examine risk escalation. Results show that the lognormal distribution provides the strongest parametric fit for vehicle counts, while the traffic Markov model achieves a one-step state accuracy of 0.720, equal to the persistence baseline but with additional probabilistic interpretability. Monte Carlo simulation indicates a high probability of encountering at least one critical traffic state within 24 hours when the current state is already critical. In the maintenance case, the probabilistic validation model achieves an area under the receiver operating characteristic curve (ROC-AUC) of 0.976 and an F1-score of 0.758. The findings show that stochastic modeling can support risk-sensitive decisions by reporting transition probabilities, uncertainty intervals, and scenario-based future outcomes.
Zitieren
APA
Shlenova, M., & Ani, M. I. (2026). Stochastic Decision Support under Uncertainty: Markov Transitions and Monte Carlo Simulation. Qubahan Educational Journal, 3(4), 1-16. https://doi.org/10.48161/qej.v3n4a22
Vancouver
Shlenova M, Ani MI. Stochastic Decision Support under Uncertainty: Markov Transitions and Monte Carlo Simulation. Qubahan Educational Journal. 2026;3(4):1-16. doi:10.48161/qej.v3n4a22
BibTeX
@article{Shlenova2026,
author = {Shlenova, Maryna and Ani, Mercy Ifunanya},
title = {Stochastic Decision Support under Uncertainty: Markov Transitions and Monte Carlo Simulation},
journal = {Qubahan Educational Journal},
year = {2026},
volume = {3},
number = {4},
pages = {1--16},
doi = {10.48161/qej.v3n4a22}
}
EUVIMED