IDENTIFYING THE SUCCESS FACTORS FOR AI-SUPPORTED CRISIS MANAGEMENT IN PUBLIC SECTOR IN PALESTINE: A MULTI-CRITERIA DECISION-MAKING APPROACH

Abstract

Integrating artificial intelligence (AI) into public sector crisis management poses a substantial institutional challenge, especially within resource-constrained situations with fragmented data infrastructure, underdeveloped personnel competencies, and largely absent regulatory frameworksIn order to identify and rank the key success factors (CSFs) influencing AI adoption in the Palestinian public sector, this study uses the Fuzzy Analytic Hierarchy Process (Fuzzy AHP) as its primary methodological framework, utilizing Chang's (1996) extent analysis method to calculate criteria weights. 14 domain experts from 12 Palestinian public sector organizations were given structured pairwise comparison tools; 14 of them were kept in the final analysis after the data quality was evaluated. Technical and Organizational Factors, Ethical Factors, and Training and Capacity-Building Factors are the three hierarchical dimensions in which the instrument produced 778 individual judgments among 19 sub-factors. Chang's extension analysis and geometric mean aggregation analysis resulted in a hierarchy of priorities. With 53.28% of the total important weight, Training and Capacity-Building Factors are the dominant dimension. Among the 19 sub-factors in this category, Skill Level of Personnel received the greatest priority within the Palestinian public sector (65.95% local weight; 35.14% global weight), providing clear factual proof of a key basic competency shortage. The Internet of Things infrastructure (22.72% local weight), Deep learning (21.84%), and Large-scale Machine Learning (19.80%), which together account for 64.36% of the technical category's internal weight, lead Technical and Organizational Factors, which came in second (35.15%). Reliability and Safety (18.88%) and Accountability (18.82%) were determined to be the most important governance criteria, while Ethical Factors obtained the lowest category weight (11.56%). The lack of a thorough AI regulatory framework in the Palestinian legal system is reflected in the weight of 0.00% given to regulatory training. These results, which were confirmed by sensitivity analysis in three analytical scenarios with ±20% weight perturbations, provide an evidence-based, sequentially structured framework for adoption: technological investment must be conditioned and preceded by foundational workforce development. The four pairwise comparison matrices all fulfilled the Consistency Ratio (CR) of < 0.10. The methodology is transferable to similar developing-country contexts with comparable institutional and infrastructure problems.