Artificial intelligence (AI) is a powerful tool for asset managers, especially quant funds. But there are few quick wins. Investment in people and infrastructure, research, and patience, are all required to outperform the market.
Armed with many new data sources, as well as cheap and increased computing power and data storage facilities, scientists have been able to advance the primary AI techniques in use today – neural networks, support vector machines, and random forests – and their applications, very rapidly over the last few years.
Their use and sophistication have also increased because many developers have made the tools used to build them available as open source software. As a result, organizations can test AI techniques in real world situations without developing their own algorithms from scratch.
Deep neural networks, which fall into the machine learning subset of AI, have recently produced impressive results and found widespread application: playing classic board games, image recognition, natural language processing, and, of particular relevance to asset management, making predictions from data.
Like a human brain, deep neural networks learn by practice and feedback, not by processing a long set of handcrafted rules. This makes it a powerful tool in asset management. When market characteristics change, a neural network can adjust its calculations accordingly.
Icing on the Alpha Cake: Improved Trade Execution
“Buy 1,000 shares in Company X today.” This might be the trading instruction generated by an alpha strategy which has established that there is a high probability of a price increase over the next week.
But should all 1,000 shares be purchased at once, accepting the current offer price in the market? Or, should the order be split up, and multiple smaller orders be placed throughout the day? It’s an ideal problem for a deep neural network. The order book data of exchanges – including prices, volumes, and timing priorities of buyers and seller of every traded financial instrument – are vast, publicly available, structured, and continuously changing.
CFM’s algorithms have been trained to analyze this order book data and determine how to minimize the costs of executing a trade. The algorithms learn how to do this given any kind of shape, size, or dynamic or order books. And they determine execution rules for any kind of financial instrument, including stocks, bonds, futures, and options.
Once trained, the algorithm interacts with the market. In doing so, it might establish that the price is likely to decline slightly within the next two minutes, so it delays executing the buy order. At an individual trade level, the savings are tiny. But over time, shaving a few percentage points off the trading costs of a large book with a high volume of trades can significantly boost returns.
Previously impossible analyses
In the fundamental research function of asset management, AI powered tools can now be deployed to conduct analyses that were previously impossible to do. Algorithms can scan the web; read and interpret millions of documents and audio clips; recognize sentiment in text or voice; and even identify “noisy” activity levels that might indicate an area requiring further research, such as a spike in discussions, patents, or academic papers about a new technology.
Then they need to provide this feedback to research analysts.
Machines, even AI-powered machines, are essentially very efficient tools for doing one thing, and are nowhere near replacing humans for many higher-level functions. They are also not going to start a project on their own – at least not in the near future – so, in many areas of asset management, humans are and will for some time to come still be needed to initiate, guide, and provide context to the work performed by machines.
An edge for quants, but difficult to capture
For quantitative investment managers, techniques such as deep neural networks are an addition to the existing quantitative investing toolkit. At CFM, all quantitative techniques, whether they use AI or not, are applied in some combination to generate alpha. They can also be very effective to reduce the cost of trading, as noted in the above sidebar.
It is now technically and economically feasible to analyze vast amounts of data that might impact the future price of a financial instrument, including:
- Pricing data at a very granular level from exchanges all over the world
- Fundamental data, such as financial results, sector and macroeconomic trends
- “Exotic” data, such as investor sentiment derived from social media, the state of crops derived from satellite images, or usage trends of electronic devices derived from the Internet of Things.
It is an extremely complicated task to implement these techniques to predict prices, and thus there are few quick wins. CFM’s researchers and data scientists are constantly fishing in new data sets and testing new techniques, which quite often produce only incremental improvements to the alpha strategy. For example, from a data set of approximately 1.5 million daily financial “stories” generated – ranging from concise tweets to in-depth articles – only about 100 would have a discernable impact on prices and would be worth incorporating into a trading algorithm. But the algorithms do uncover many needles in the data haystack.
The final decision to execute a trade is based on an aggregation of hundreds of signals, which indicate the degree of bias for a price to move in a particular direction. It won’t result in a profitable trade every time, but it is stacking the odds in favor of one.
And when this is aggregated across the many trades executed by CFM, alpha is generated.
However, the algorithms also require continual checking to monitor their performance. A neural network is effectively a “black box” which generates trades that are not possible to fully explain. This is a less comfortable situation than with the more transparent algorithms that are traditionally used, so advanced statistical techniques are used to measure their performance –against benchmarks or against existing systems – to help decide if an underperforming system needs to be modified or switched off.
Hype around AI at a crescendo
The commercial potential of AI is enormous. But in asset management, trading results are likely to improve only gradually, and will only be significant when measured over a long period of time.
For CFM, AI is simply another tool in the diverse quantitative toolbox it has been developing for over 25 years. In a systematic and disciplined fashion, CFM analyses the latest data sets, algorithmic techniques, and hardware to establish how they can be deployed to improve investment returns over the long term.
It is easy to get up and running with AI today. The difficult part is building up the expertise in all of the fields required to exploit it creatively while avoiding the painful traps. CFM has done this by combining teams of researchers, data scientists, and investment experts to ensure that technology is used, but not abused, to its potential.
In short, a tremendous amount of hard work and long-term commitment – by humans – is needed for investors to realize the benefits of AI.
ANY DESCRIPTION OR INFORMATION INVOLVING INVESTMENT PROCESS OR ALLOCATIONS IS PROVIDED FOR ILLUSTRATIONS PURPOSES ONLY.
ANY STATEMENTS REGARDING CORRELATIONS OR MODES OR OTHER SIMILAR STATEMENTS CONSTITUTE ONLY SUBJECTIVE VIEWS, ARE BASED UPON EXPECTATIONS OR BELIEFS, SHOULD NOT BE RELIED ON, ARE SUBJECT TO CHANGE DUE TO A VARIETY OF FACTORS, INCLUDING FLUCTUATING MARKET CONDITIONS, AND INVOLVE INHERENT RISKS AND UNCERTAINTIES, BOTH GENERAL AND SPECIFIC, MANY OF WHICH CANNOT BE PREDICTED OR QUANTIFIED AND ARE BEYOND CAPITAL FUND MANAGEMENT’S CONTROL. FUTURE EVIDENCE AND ACTUAL RESULTS COULD DIFFER MATERIALLY FROM THOSE SET FORTH, CONTEMPLATED BY OR UNDERLYING THESE STATEMENTS. THERE CAN BE NO ASSURANCE THAT THESE STATEMENTS ARE OR WILL PROVE TO BE ACCURATE OR COMPLETE IN ANY WAY. ALL FIGURES ARE UNAUDITED.