A decision support system developed during the COVID-19 pandemic to optimize vaccine distribution across Iran's 90 million population. This tool was presented to the Iranian Ministry of Health and addressed critical resource allocation challenges during a national health crisis.
During the pandemic, Iran faced two major challenges:
- Supply Optimization: How to fairly distribute limited vaccines across 30 provinces and 429 districts?
- Demand Prioritization: How to identify and prioritize high-risk individuals among 90 million citizens?
This system combines statistical modeling with operational optimization:
- Risk Scoring Engine: Beta coefficients from regression analysis (death as dependent variable) to calculate individual risk scores
- Allocation Algorithm: Optimization model for provincial and district-level vaccine distribution
- Excel-Based Interface: User-friendly frontend built with VBA for government stakeholders
- Backend: VBA for complex calculations and optimization logic
- Frontend: Excel forms for data input and visualization
- Data Processing: Handles national-scale demographic and health data
- Population-Scale Analysis: Processes data for 90 million individuals
- Real-Time Optimization: Dynamic allocation based on changing vaccine supply and risk factors
- Government-Ready Interface: Designed for non-technical ministry staff
- Crisis Response: Deployed during peak pandemic pressure
- Adopted by Iranian Ministry of Health for national vaccine distribution planning
- Addressed critical public health decision-making during emergency conditions
- Demonstrated ability to deliver production-ready systems under pressure
- Microsoft Excel with macros enabled
- Input data in specified format
- Download the
.xlsmfile from releases - Prepare input data with risk factors and population metrics
- Run the macro to generate allocation recommendations
.basfiles contain the core VBA logic- Modular design allows for customization
- Commented code for easy understanding
The system uses regression analysis to identify risk factors correlated with COVID-19 mortality, then applies optimization algorithms to maximize lives saved given supply constraints.
This project demonstrates:
- Scalable system architecture for national-level problems
- AI/optimization techniques applied to real-world crises
- Cross-functional collaboration between technical and government teams
- Impactful technology deployment in high-stakes environments
Part of a portfolio of systems developed for government and international organizations during crisis response.
