Modeling Impacts of Cyberattacks on Financial Assets Valuation

This research aims to create a platform that can predict the impacts of cyberattacks on various financial assets, such as bonds, stocks, and a company’s credit risk. The focus is on the impacts of cyberattacks on the prices of financial assets listed on the Toronto Stock Exchange (TSE). Still, the prediction models and tools developed should also be applicable to assets listed in other comparable markets. The project has four main objectives: understanding the relationship between the type, impact, and severity of cyberattacks and trading activities; modelling the behaviour of liquidity providers in response to major cyberattack news; modelling the longterm impacts of cyberattacks on companies’ credit risk; and devising an ensemble of deep learning agents to predict the price movement of companies’ stocks, bonds and offer real-time trading signals. This research makes significant contributions to machine learning-based modelling of the effects of rare events on financial asset pricing, specifically focusing on the short and long-term impacts of cybersecurity attacks.

Faculty Supervisor:

Davar Rezania

Student:

Partner:

Cyber Maple Ltd

Discipline:

Business

Sector:

Professional, scientific and technical services

University:

University of Guelph

Program: