Deep Learning in Quantitative Finance

In Deep Learning in Quantitative Finance, XVA expert and quantitative finance and development practitioner Andrew Green delivers a startlingly insightful and up-to-date discussion of how to apply deep learning to quantitative finance. The author offers a complete resource on how deep learning is used in quantitative finance applications, introducing the basics of neural networks-- including feedforward networks, optimization, and training--before covering more advanced topics.

Deep Learning in Quantitative Finance dives into advanced deep learning topics, including sequence models, generative AI--like VAEs, GANs, and diffusion models -- and deep reinforcement learning.

You'll explore the latest deep learning research in quantitative finance, like approximate derivative values, solve PDEs and BSDEs with neural networks, enhance Monte Carlo models with deep learning, use deep semi-static replication for Bermudan and American options, map credit curves and generate exposure profiles, calibrate models and volatility surfaces, generate realistic market data, apply hedging methodologies and develop predictive market models. It offers case studies and access to a hands-on, companion GitHub repo complete with Jupyter notebooks containing working and tested Python code examples.

Perfect for quantitative finance practitioners interested in getting involved with deep learning in a practical and hands-on way, Deep Learning in Quantitative Finance is a practical handbook on a subject that will likely become even more influential in the field than it is today.