This research investigates a method of urban building energy simulation (UBES) by integrating Building Information Modeling (BIM), building simulation, and algorithm-based prediction to forecast the impact of surrounding conditions. In the urban context, building energy performances are determined not only by the individual building design but also by the building's surrounding context. Many energy performances are sensitive to outdoor and surrounding building conditions, such as neighbouring building volumes, heights, and spaces between buildings. However, such surrounding conditions were overlooked because they can exponentially increase the complexity of urban modeling and simulation. In that regard, the research sought to investigate a novel framework to take advantage of accurate performance simulations and algorithm-based fast predictions. This paper presents our UBES method implemented from three research phases: (i) building a parametric urban model in BIM to provide simulation inputs, (ii) creating a parametric simulation interface to produce training and validation data, and (iii) creating a prediction interface using a Support Vector Machine (SVR) algorithm. Lastly, the paper elaborates on the findings from the prediction results.