BACKGROUND AND OBJECTIVES: Decision-making in Building demolition is complex, involving structural, environmental, economic, and regulatory considerations. Traditional approaches often rely on subjective judgment and lack data-driven analysis. This study seeks to create a comprehensive decision-support framework that integrates Building Information Modeling and Bayesian Networks to optimize go or no-go decision processes. The objectives of the study were to provide a more accurate, reliable, and systematic tool that improves planning, reduces uncertainty, and promotes safety, efficiency, and sustainability in Building demolition practices.METHODS: This study integrates Building Information Modeling data with Bayesian Network probabilistic analysis to assess structural, environmental, and managerial factors influencing demolition decisions. A case study was conducted on a three-story market Building located in South Jakarta. Expert insights were utilized to create conditional probability tables, improving the model's precision and its applicability to actual demolition situations. The model was validated through simulation and sensitivity analysis, identifying key variables affecting go or no-go outcomes.FINDINGS: The integrated Building Information Modeling–Bayesian Network model effectively supports go or no-go demolition decisions by addressing uncertainty and risk factors probabilistically. According to the case study findings, there is a 55.10 percent chance of demolition, influenced by inadequate structural integrity (70 percent) and significant retrofit costs (59 percent). Mechanical demolition was preferred (56 percent) for its efficiency and lower risk. Sensitivity analysis identified structural integrity, retrofit cost, Building age, environmental impact, and permit status as key influencing variables. Validation by experts has established the model's practical importance, illustrating its potential to boost planning accuracy and encourage sustainable, data-centric decision-making in complex urban demolition endeavors.CONCLUSION: Integrating Building Information Modeling and Bayesian Network improves demolition decision-making by addressing uncertainty and supporting risk-informed analysis. The model boosts the precision of planning and aids in pinpointing significant influencing factors, like structural integrity and the costs associated with retrofitting. Furthermore, it fosters sustainable, data-driven approaches, rendering it an effective tool for complicated urban demolition initiatives.