Abstract: The software industry necessitates early prediction of software defects for effective quality assessment and resource allocation. During the initial stages of the software development life cycle (SDLC), failure data is often unavailable. Consequently, the insights of domain experts can be crucial in estimating potential software defects during these early phases. This paper introduces a model designed to forecast software defects prior to the testing phase, emphasizing the structure of the software development process. The model is developed using metrics derived from early artifacts of the SDLC. The development and experimental aspects of the model are presented through the application of a Bayesian belief network (BBN). The qualitative aspects of software metrics, along with expert opinions, form the core of this methodology. To demonstrate the practicality and effectiveness of the proposed approach, ten datasets from real software projects have been utilized. The analysis and validation of predicted software defects, based on varying levels of uncertainty from domain experts, are compared against actual defect occurrences.