Name in original language
استشراف
Initiative overview
Over recent years, SDAIA led national efforts to centralise government data through the National Data Bank (NDB), creating a unified platform for secure data sharing and integration across public-sector entities. This provides access to large volumes of administrative, economic and sectoral data from multiple systems. Estishraf was established to leverage this foundation, applying artificial intelligence and advanced analytics to transform integrated datasets into actionable insights that support evidence-based policymaking and strategic planning.
Estishraf enables government entities to analyse integrated public-sector data and apply AI for complex policy analysis. Machine learning models and advanced methods detect patterns, forecast socio-economic trends, evaluate policy impacts and simulate alternative scenarios before implementation. Policymakers can examine cross-sector relationships spanning education, labour markets, transportation, housing and industry within a unified analytical environment. Workflows that previously required extensive manual effort are now executed rapidly on integrated national data, allowing faster responses to policy questions and significantly improving productivity and analytical depth.
Since its establishment, Estishraf has supported more than 1.9k analytical projects across sectors. It also strengthens government analytical capacity by providing an advanced environment where data scientists, economists and policy analysts work with integrated datasets and modern infrastructure. Access to large-scale, cross-sectoral data and sophisticated tools supports attracting and retaining highly specialised talent in AI and data science.
Illustrative AI applications include using machine learning on national traffic safety data to identify high-risk locations, contributing to a reduction in road fatalities of over 60% compared to 2016 levels, lowering mortality from 28.8 to below 10 per 100,000. Computer vision models analyse street-level imagery to detect and monitor visual pollution, enabling municipalities to identify violations and improve urban environments. In housing, machine learning clustering models applied to real estate, demographic and purchasing power data segment markets and estimate idle land supply, supporting policy simulation and calibration of the Idle Land Program. Additional analyses link education outcomes with employment and wage data to identify labour-market skill gaps.
Estishraf demonstrates how governments can translate data and artificial intelligence into a practical national capability for policy analysis and strategic foresight.
