Autonomous Trading

A few weeks ago while I was at a quantitative finance conference, I had the pleasure of meeting a young man named William Mok, one of the co-founders of Tech Trader fund. At the ripe young age of 22, he had managed to develop and implement a fully autonomous trading system. What makes his system so unique compared to the thousands of other systematic trading systems in the markets is the inherent human element he claims it possesses.

A simple way to understand this is by looking at the process of walking across the street. A quantitative system would crunch thousands of numbers assessing the probability of a car crossing the street; the time of day, the temperature, the color of the grass etc... His system, Tech Trader, would simply look down the street to see there is no car, making it physically impossible to get hit. It leverages technology to do what the best traders do at scale and at maximum efficiency. But how exactly does it do this?

He claims the system contains three layers of artificial intelligence. The first, a layer of machine learning which acts like an extra pair of senses for a human like system. The second, a layer of reinforcement learning, abstracts the majority of the data and analyses it. This layer also helps the system learn from its past experiences (but only from its past experiences). This takes the form of Q-learning, a form of reinforcement learning used to find an optimal solution for a given set of decisions. The missing piece that ties the system together is the third layer. This layer helps the computer simulate human like qualities of dreaming, imagination and reflecting, storing the data like memories. It doesn't only consider what has happened but what could happen.

What I found most surprising are the stages of evolution of the system. He had told me that when the system first rolled out, it had a tendency to take a very high risk strategy approach, trading multiple times a day in and out of large positions. But as it gained data and information, it began taking a much more conservative trading approach, flattening out its overall variance over time.

The scope computer science has on finance is boundless in its limitations. As long as there are people like William Mok who are willing to continue to innovate and think outside the box, finance will continue to move forward in more exciting ways than any could even imagine.

Image References:
https://media.licdn.com/mpr/mpr/p/4/005/09c/368/3730a17.jpg

Quantum Computing & Finance

Quantum computing is a field of research that allows us to study how algorithms and systems can apply quantum phenomena to derive solutions to complex mathematic problems. It was a field pioneered by Paul Benioff and Richard Feynman in the early 1980's. What makes quantum computers so computationally powerful is its stochasticity, i.e. on its simplest level, they operate with random variables, making them much more robust when trying to efficiently compute large complex systems involving probabilistic variables. The quantum computer relies on storing qubits, the memory elements that hold a linear superposition of the possible combinations of {(0,1)}. This allows it to evaluate and store all feasible solutions (combinations) of 0 and 1 simultaneously.

The characteristics outlined above make quantum computing ideal for solving problems that require parallel processing, the use of more than a single source of computation to execute a program or threads for example. A very useful application of quantum computing in finance is scenario analysis, where the goal is to evaluate a distribution of outcomes under an extremely large number of scenarios. The beauty of quantum computers is that they don't evaluate solutions sequentially like normal computers do, they solve them by assessing the linear combinations of possible solutions (i.e. the 0's and 1's for each qubit) all at the same time. Many current approaches to the problem require far too much time, computing power or are too restrictive in their models.

Quantum computing is no longer a thing of the past. NASA, Google, Lockheed Martin and even Berkeley have obtained their very own quantum computers. The very first company to make these computers is called D-wave systems with their flagship product the D-wave machine (pictured below). These computers are kept in chambers with temperatures below 15 millikelvin. To put that into perspective, it is 180 times colder than interstellar space making it, quite literally, one of the coolest places in the universe. The reason for keeping such low temperatures is so the solution to problems given to it automatically converge to those that require the minimum energy state.

Quantum computers are the future of finance. Many models used in finance today do not map very well onto the real world (requiring a degree of complexity and robustness simple models cannot satisfy). They help us compute solutions to models cognisant of reality's complexity and free us from an over reliance of dumb-downed models and heuristics.

Image References: 

https://static01.nyt.com/images/2013/05/16/technology/16bits-sub-quantum/16bits-sub-quantum-tmagArticle.png