Generative Adversarial Networks (GANs) are powerful AI algorithms capable of creating artificial data closely mimicking the statistical properties of actual data. GANs consist of a generator network that generates the data and a discriminator network that tries to distinguish between the real and the artificial. Students will explore GAN fundamentals, implement GANs in Python TensorFlow and experiment with various architectures, fine-tune parameters to produce high-quality synthetic financial time series data. This opportunity offers hands-on experience at the intersection of AI and quantitative finance, enhancing coding and data manipulation skills and the understanding of the statistical properties of real financial time series data.