@article{4718,
  author = {P Paramasivaiah},
  title = {Modeling Oil Price Shocks and Global Economic Vulnerability During the 2026 US-Iran Conflict: A Time-Series, Machine Learning, and Diffusion-Based Approach},
  journal = {Journal of Information Technology Review},
  year = {2026},
  volume = {17},
  number = {2},
  doi = {https://doi.org/10.6025/jitr/2026/17/2/80-99},
  url = {https://www.dline.info/jitr/fulltext/v17n2/jitrv17n2_3.pdf},
  abstract = {This study investigates the impact of oil price shocks on global economic vulnerability during the hypothetical
2026 US-Iran conflict, specifically focusing on the closure of the Strait of Hormuz. Integrating time-series
decomposition, machine learning, and diffusion-based modeling, the research analyzes crude oil price
dynamics and their macroeconomic consequences. The methodology employs seasonal trend decomposition,
change-point detection, and an adapted robust SEIR framework to track shock propagation across nations.
Additionally, hybrid machine learning models utilizing Gradient Boosting and Random Forest algorithms
forecast price spikes and volatility.
Results identify significant structural breaks on March 4 and March 9, 2026, coinciding with conflict escalation
and driving Brent crude to $104 per barrel. The SEIR model categorizes economies into Susceptible, Exposed,
Infected, and Resilient states, revealing high vulnerability in South Asian nations like Pakistan and Bangladesh
due to import dependence. Scenario analysis projects GDP contractions ranging from -1.62% in the best-case
de-escalation to -28.80% for Iran under prolonged conflict. Crucially, findings indicate that early policy
interventions can reduce economic damage by 30-40%. The study concludes that combining diffusion models
with machine learning enhances forecasting accuracy under geopolitical uncertainty. It emphasizes that
shock severity depends not only on market dynamics but also on policy responsiveness, urging coordinated
strategic reserve releases and rapid diplomatic action to mitigate systemic risks in energy-dependent
economies. Future research should incorporate longer historical datasets to further refine predictive
capabilities},
}