Applications of Tensor Neural Networks to pricing early-exercise options

An early-exercise option is a financial agreement which grants one party the right, but not the obligation, to buy or sell an underlying asset at a pre-agreed price at a series of pre-determined times. The problem of pricing an option is of great practical importance and is typically addressed using computationally expensive numerical simulation methods. We will apply cutting edge Deep Learning techniques to address this fundamental problem. Once trained, the models we develop will be able to solve the option pricing problem in a fraction of the time taken by industry-standard classical approaches. The main contribution of our work will be to leverage Tensor Networks to alleviate the computational cost of training the models in the first place. The partner will benefit from this project by developing their software stack to tackle this commercially valuable problem.

Faculty Supervisor:

Dmitry Panchenko

Student:

Partner:

Multiverse Computing

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

University of Toronto

Program: