Systematic review reveals parametric and machine learning models dominate computational façade design, highlighting the need for transparent, hybrid systems.
As building façade design becomes increasingly complex and requires consideration of multiple factors, the use of computational techniques has attracted substantial research interest. This paper presents a systematic literature review of computer-aided architectural design (CAAD) methods for building façades. A total of 133 articles published between 2015 and 2025 were analysed using quantitative and descriptive approaches. Based on the research methodologies employed, the applications of CAAD in façades can be categorised into three thematic groups: rule-based (12.4%), parametric/hybrid modelling (66.2%), and generative machine learning-based methods (21.4%). The analysis reveals the current research trends and highlights the strengths and limitations of different CAAD methods. To address the identified gaps in knowledge, future work is expected to integrate CAAD methods for complementary advantages, improve the transparency of CAAD methods, and leverage advanced computing technologies and interactive design patterns to improve design efficiency.
No takes yet. Share an insight, caveat, or question.
Zhan et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: