Modern advancements in mathematical analysis, computational hardware and software, and availability of big data have made possible commoditized machines that can learn to operate as investment managers, financial analysts, and traders. We briefly survey how and why AI and deep learning can influence the field of Finance in a very general way. Revisiting original work from the 1990s, we summarize a framework within which machine learning may be used for finance, with specific application to option pricing. We train a fully-connected feed-forward deep learning neural network to reproduce the Black and Scholes (1973) option pricing formula to a high degree of accuracy. We also offer a brief introduction to neural networks and some detail on the various choices of hyper-parameters that make the model as accurate as possible. This exercise suggests that deep learning nets may be used to learn option pricing models from the markets, and could be trained to mimic option pricing traders who specialize in a single stock or index. 1 Artificial Intelligence: A Reincarnation Artificial intelligence (AI) is in its second new age. While the notion that machines are capable of exhibiting human levels of intelligence saw its beginning implementations in the 1950s, success in creating AI machines was thin, and mostly, AI was deemed to be a failed enterprise. In the past few years, there has been a resurgence of AI, ∗Robbie Culkin is an undergraduate Computer Science and Engineering student, and Sanjiv Das is Professor of Finance and Data Science. They may be reached at rculkin@scu.edu, srdas@scu.edu.
[1]
Matus Telgarsky,et al.
Benefits of Depth in Neural Networks
,
2016,
COLT.
[2]
W S McCulloch,et al.
A logical calculus of the ideas immanent in nervous activity
,
1990,
The Philosophy of Artificial Intelligence.
[3]
P J Webros.
BACKPROPAGATION THROUGH TIME: WHAT IT DOES AND HOW TO DO IT
,
1990
.
[4]
S. Dreyfus.
The computational solution of optimal control problems with time lag
,
1973
.
[5]
F. Black,et al.
The Pricing of Options and Corporate Liabilities
,
1973,
Journal of Political Economy.
[6]
Henry J. Kelley,et al.
Gradient Theory of Optimal Flight Paths
,
1960
.
[7]
Geoffrey E. Hinton,et al.
Learning representations by back-propagating errors
,
1986,
Nature.
[8]
W. Pitts,et al.
A Logical Calculus of the Ideas Immanent in Nervous Activity (1943)
,
2021,
Ideas That Created the Future.
[9]
Paul J. Werbos,et al.
Backpropagation Through Time: What It Does and How to Do It
,
1990,
Proc. IEEE.
[10]
Kurt Hornik,et al.
Approximation capabilities of multilayer feedforward networks
,
1991,
Neural Networks.