Please find below the notes from GAM Investments’ Weekly Investment Meeting held on 3 October 2018 – this week’s speaker was Hasan Amjad, who described the growing importance of artificial intelligence and machine learning in systematic trading.
Artificial intelligence (“AI”) as a field of research began in the middle of the 20th century. AI as a concept has a wide number of applications, including in the field of systematic investing. AI, big data (“BD”) and machine learning (“ML”) are increasingly being used by managers seeking to gain an edge by processing vast amounts of data to inform investment decisions. At this point in time, the use of the term AI in systematic investing practically means the use of ML, in relation to investment decisions, and the two are often used interchangeably. ML constitutes a smorgasbord of statistical techniques which have finally got to the stage where they are becoming extremely useful in the real world.
In terms of trade execution, there are three clearly identifiable stages (pre-trade analytics, algorithmic trading and transaction cost analysis) and, at GAM Systematic, we use AI in each. So, let us begin with the first of these stages, which takes place prior to the execution of the trade. At this point, we know that we want to buy or sell a certain amount of a given asset, so the objective of pre-trade analytics is to determine the best way of doing this before implementation begins. The technology we use here analyses the many different methods of executing the trade. Some trade algorithms, for example, work best with small orders while others are most effective when applied to individual markets / assets. Using AI helps us determine the distribution of pay-offs from each algorithm and, with the passage of time, helps us to maximise those pay-offs and optimise trade execution.
In respect of algorithmic trading, our motivation is to improve the accuracy of price prediction. This is beneficial because, when buying an asset, we would naturally want to execute quickly if probability analysis implies that the price is likely to rise. Conversely, if the price is likely to fall, we would prefer to take our time and allow the market to move in our favour. AI technology can help us determine such probabilities.
Finally, having used one system for choosing algorithms and another for predicting prices, the third stage of the process (transaction cost analysis) is all about determining whether the systems work in practice and, if so, quantifying that beneficial impact. This can be achieved by comparing the results attained when the tools are turned on with those where they are switched off. The important point is that this is a real comparison that generates hard numbers, rather than looking at actual results against those of a theoretical back-test using computational scenario analysis. We are able to undertake such comparisons because we execute thousands of trades a day and can therefore collect a lot of data within a short space of time. It is also crucial to use this trading context when interpreting the results because the cost-savings on any given trade execution will be minimal, yet compound incrementally, over thousands of trades a year, to potentially deliver a meaningful cost saving which can ultimately be passed on to investors through enhanced net-of-cost returns.
Important legal information
The information in this document is given for information purposes only and does not qualify as investment advice. Opinions and assessments contained in this document may change and reflect the point of view of GAM in the current economic environment. No liability shall be accepted for the accuracy and completeness of the information. Past performance is no indicator for the current or future development.
Important Information on Systematic Investing: Important Information on Systematic Investing: Systematic investment strategies are speculative and are not suitable for all investors, nor do they represent a complete investment program. Many of the investment programs are speculative and entail substantial risks. Systematic investment strategies includes the risks inherent in an investment in securities, the use of leverage, short sales, options, futures, derivative instruments, investments in non-US securities and “junk” bonds. There can be no assurances that an investment strategy (hedging or otherwise) will be successful or that a manager will employ such strategies with respect to all or any portion of a portfolio. Investors could lose some or all of their investments.