AI-Driven Decision Support Systems for Strategic Planning: A Multi-Criteria Optimization Framework Integrating AHP, TOPSIS, and Machine Learning

Abstract

This study develops a hybrid decision support system (DSS) that integrates artificial intelligence with multi-criteria decision-making techniques to enhance strategic planning in complex and uncertain environments. The research addresses key limitations of traditional DSS models, particularly their reliance on static criteria weighting and lack of adaptive capabilities.The proposed framework combines the Analytic Hierarchy Process (AHP), the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), and machine learning to enable structured and adaptive decision-making. A synthetic dataset of 120 strategic scenarios was constructed to simulate realistic organizational conditions. The methodology includes consistency validation (AHP), multi-criteria ranking (TOPSIS), and predictive optimization using supervised learning models implemented in Python. Results show that the integrated model significantly improves decision quality, consistency, and adaptability, outperforming traditional approaches. Machine learning enhances the robustness of evaluation processes and enables dynamic adjustment of decision outcomes. This study contributes to the advancement of intelligent decision systems by bridging operations research and artificial intelligence, providing a scalable and reproducible framework for strategic decision-making.