Hedonic modelling is essential for institutional investors, researchers and urban policy-makers in order to identify the factors affecting the value and future development of rents over time and space. While statistical models in this field have advanced substantially over the last decades, new statistical approaches have emerged expanding the conventional understanding of real estate markets. This paper explores the in-sample explanatory and out-of-sample forecasting accuracy of the Generalized Additive Model for Location, Scale and Shape (GAMLSS) model in contrast to traditional methods in Munich’s residential market. The results show that the complexity of asking rents in Munich is more accurately captured by the GAMLSS approach, leading to a significant increase in the out-of-sample forecasting accuracy.