English
Performance-based budgeting (PBB) remains one of the most critical challenges in modern public expenditure management, particularly as governments transition toward data-driven and intelligent governance systems. Advances in artificial intelligence now allow budgeting processes to move beyond subjective estimates and toward analytical, transparent, and evidence-based decision-making. This study introduces an AI-enabled hybrid framework for PBB that integrates Artificial Neural Networks (ANN) with robust linear optimization to support smart governance and resilient resource allocation. The ANN component learns complex cost–activity relationships from historical organizational data and generates predictive estimates for future costs and cost drivers, which are among the primary sources of uncertainty in budgeting. These ANN-derived uncertainty intervals are then incorporated into a robust optimization model following Soyster and Bertsimas–Sim formulations to ensure both feasibility and optimality under uncertain conditions. The proposed hybrid model provides a transparent and intelligence-driven mechanism for allocating resources in alignment with organizational goals. The framework
Sign in with your free account to read, download EPUBs or listen.
Ameneh Khadivar; Saba Abdian · CC BY 4.0
Ebook · AI-Enabled Robust Performance-Based Budgeting: A Hybrid Neural–Optimization Approach for Smart Governance · Ameneh Khadivar; Saba Abdian · Internet Archive
Smart Governance · AI-Enabled Budgeting · Performance-Based Budgeting (PBB) · Robust Optimization · Artificial Neural Network