In this project, students will delve into the innovative world of machine learning and explore the capabilities of Variational Autoencoders (VAEs) to create synthetic data. VAEs are cutting-edge generative models that excel in capturing complex data distributions and generating new samples that closely resemble the original data. Through hands-on experience, participants will develop a deep understanding of VAEs' architecture, training methodologies, and their role in data augmentation. By mastering this technique, students will contribute to solving real-world challenges in various fields where data scarcity is a concern. Join us in this project to unlock the potential of synthetic data generation using VAEs and make a meaningful impact on applications ranging from financial market modeling to asset pricing to anomaly detection and beyond.