Progress in reducing the energy demand of the building sector through existing measures, such as the development of energy-efficient buildings (EEBs) and stringent building energy regulations, is insufficient to achieve the objectives of the Paris Agreement. Therefore, novel approaches are needed to accelerate the energy demand reduction of the building sector, especially those related to the lack of widespread adoption of EEBs as a result of their marketing failure. Increasing the number of EEBs with better marketability strategies through aesthetic enhancement can accelerate the reduction of energy demand in the building sector. In this regard, this study aims to investigate the impact of different window features (i.e. position, number, area, width, height, symmetry and proportion) on housings aesthetic, and marketability. It also attempts to develop computational models for their predictions. For this purpose, an artificial neural network (ANN) computational model was developed with the results of a conducted comprehensive survey (n=807). Results show a high level of accuracy (up to 95%) for the performance of ANN models in prediction of individuals' aesthetic appreciation and housing’s marketability.