Bilgi Yilmaz

• Modeling housing markets is a challenging and central research area since they are highly related to the economy. However, the limited available data prevents researchers from improving models. As an alternative, this study introduces Housing GANs, a data-driven modeling approach inspired by the recent success of generative adversarial networks (GANs). The Housing GANs include a generator and discriminator function utilizing Wasserstein GAN with gradient penalty and mitigate original housing datasets, including continuous and discrete data. The generator function predicts the real data distribution and generates realistic housing data. The empirical analysis highlights that the Housing GANs successfully learns the distribution and generate realistic housing data in high fidelity.