Deeply Learning Derivatives

2018/09/06 by Ryan Ferguson, Andrew Green, Andrew R. Green +2 · 1 citation
Computer Science · Decision Sciences · Economics, Econometrics and Finance · #68T05 #91-08 #91G20 #91G60 #Computational Finance (q-fin.CP) #FOS: Computer and information sciences #FOS: Economics and business #Financial Markets and Investment Strategies #Forecasting Techniques and Applications #Machine Learning (cs.LG) #Stock Market Forecasting Methods #cs.LG #msc:68T05 #msc:91-08 #msc:91G20 #msc:91G60 #q-fin.CP

paper · pdf · doi:10.48550/arxiv.1809.02233

openalex publication_date 2018/09/06 · arxiv created 2018/10/17 · arxiv updated 2018/10/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper uses deep learning to value derivatives. The approach is broadly applicable, and we use a call option on a basket of stocks as an example. We show that the deep learning model is accurate and very fast, capable of producing valuations a million times faster than traditional models. We develop a methodology to randomly generate appropriate training data and explore the impact of several parameters including layer width and depth, training data quality and quantity on model speed and accuracy.

Citations

• Adam: A Method for Stochastic Optimization
• The perceptron: A probabilistic model for information storage and organization in the brain.
• Generating random correlation matrices based on vines and extended onion method
• A Fast Learning Algorithm for Deep Belief Nets
• On Characterizing the Capacity of Neural Networks using Algebraic Topology
• A Nonparametric Approach to Pricing and Hedging Derivative Securities Via Learning Networks

Cited by

• An Efficient Machine Learning Framework for Option Pricing via Fourier Transform

Related

• Fast Derivative Valuation from Volatility Surfaces using Machine Learning
• Deep Joint Learning valuation of Bermudan Swaptions
• Derivative-Informed Operator Learning for Finance: On-the-Fly Greeks, Surfaces, Hedging, and Control
• Differential Machine Learning
• Deep Learning-Based Least Square Forward-Backward Stochastic Differential Equation Solver for High-Dimensional Derivative Pricing