The increasing complexity of problems and the continued growth of information and knowledge gained over decision-makers experiences must be mastered by companies and highlight the need for Intelligent (Knowledge-Based) Decision Support Systems (KBDSS) and sophisticated techniques powered by advanced and modern technologies to provide reliable and effective support. KBDSS clearly helps the decision-makers in solving similar future problems by reusing existing solutions and therefore making a decision in a short time. A significant potential way for improving the efficiency and forcefulness of KBDSS is case-based reasoning (CBR). CBR accumulates, organizes, and shares diverse knowledge resulting from experiences. However, due to the variety of the features characterizing the cases, it makes difficult to discern the most relevant ones that meet the user requirements. To overcome these limitations, CBR systems could be further optimized by Analytic Hierarchy Process (AHP) method to improve case retrieval by selecting the most significant characteristics (feature weighting). In this study, we implement a Hybrid Intelligent Decision Support System (HI-DSS) integrating CBR-AHP method. This will reduce the space and time for solutions search and enhance the recovery accuracy of CBR systems. We are experimenting with our system in a financial credit evaluation, a multi-criteria decision problem.