Abstract: This study presents a decision support system that aids the embedded system designers during the synthesis phase to select the optimal system components such as processors, memories, communication interfaces, etc., from the available huge design alternatives. The selection process should consider the configuration options available both at the system level and the micro-architectural level, along with the knowledge about the system parameters that affect the overall objectives of the system in order to satisfy the applications requirements. The focus of the Electronic Design Automation (EDA) community is towards developing an efficient strategy for aiding the system designer during the synthesis to incorporate the domain knowledge of the target architecture and to take early design decisions. The Bayesian Belief Network (BBN) based modeling framework proposed in this study attempts to resolve the existing limitation in imparting domain knowledge and provides a pioneering effort to support the designer during the process of embedded system design. Sensitivity analysis is performed for identifying the most influential parameters for the decision making and to verify the robustness of the proposed model. Case studies in support of the proposed model are presented in order to understand how the BBN can be used in the embedded system design process by propagating the evidence and arriving at inferences in such a way to ease the decision making process.