Prediction and optimal strategies in equity algorithmic trading

Trading is increasingly moving from the human world to its electronic counterpart. In this new environment the effects need to be properly understood and analyzed. Most recently the Canadian market as other developed capital markets has experienced a reduction in direct trading costs for investors but at the cost of an increase in indirect trading costs, price variability. This affects everyone either directly, such as the Royal Bank of Canadas Capital Markets department, but also indirectly through its clients, from institutional investors and fund managers to each individual investor that buys into their funds for their financial and retirement planning. Quantitative methods can be effectively leveraged to help institutions glean the most information out of increasingly higher-frequency price information which will provide a better understanding of this new market environment. The research in this proposal aims to deploy advanced optimization models that incorporate the existing uncertainty in asset prices and artificial intelligence techniques to perform this analysis. The aim is to help the Royal Bank of Canada navigate the trading environment better and at a lower cost to its clients.

Faculty Supervisor:

Roy Kwon

Student:

Razvan Gabriel Oprisor

Partner:

RBC Financial Group

Discipline:

Engineering - mechanical

Sector:

University:

University of Toronto

Program: