Modal decomposition techniques have become important mathematical methodologies in analysing complex flow physics. The data-driven methods, such as proper orthogonal decomposition and dynamic mode decomposition are used to extract coherent structures in the form of spatial modes. These methods can be applied to both numerical and experimental data to identify the characteristic dynamics of the system. However, the classical data-driven modal decomposition methods are only applicable to problems with a fixed shape and are not suitable for systems with fluid–structure interaction or systems with shape-changing geometries. In this paper we propose a novel method utilizing a conformal mapping technique to solve this issue. Through different examples with deforming geometry, the capability of the method to accurately capture the flow features is demonstrated. The proposed method is found to be suitable for a wide range of applications and a possible candidate for reduced-order flow modelling of complex shape-changing systems.