What we learnt building an enterprise-blockchain startup

[ crypto ]

It has been almost a year since the idea of HyperVault was first conceived. In that time, we built HyperVault up from a single sentence, gained and lost team members along the way, developed a functional proof-of-concept over the short winter holidays, crashed out of a few competitions (also won a couple of prizes), and finally decided to open source. This post aims to be an honest reflection on the journey – highlighting both the good bits and the times we wanted to give up. Read more...

Graph algorithms and currency arbitrage, part 2

[ quant ]

In the previous post (which should definitely be read first!) we explored how graphs can be used to represent a currency market, and how we might use shortest-path algorithms to discover arbitrage opportunities. Today, we will apply this to real-world data. It should be noted that we are not attempting to build a functional arbitrage bot, but rather to explore how graphs could potentially be used to tackle the problem. Later on we’ll discuss why our methodology is unlikely to result in actionable arbitrage. Read more...

Graph algorithms and currency arbitrage, part 1

[ quant ]

In this post we briefly outline how graph theory can be used to systematically find arbitrage opportunities in foreign exchange markets. Read more...

Portfolio optimisation: lessons learnt

[ quant ]

Over the past few months I have been busy doing a mixture of blockchain consulting and quantitative finance research. In particular, I have had the opportunity to investigate the interesting problem of portfolio management for cryptoassets – it was not my first experience with portfolio optimisation, having implemented efficient frontier portfolios at a roboadvisor startup, but this time I took the opportunity to do a deep dive into the subject. Read more...

Exponential Covariance

[ quant ]

In this post, I describe a method of computing covariance matrices that gives additional weight to recent observations. This is particularly important in the field of financial portfolio optimisation, wherein a better estimate of future covariance can create significant value. Read more...

Stormy Seas for Proof of Work

[ crypto ]

In this post we will be examining one of the main problems with Proof of Work (PoW) – not the energy inefficiency (as it is debatable how much of a problem this really is), but something more fundamental with the consensus process. In the past couple of months we have seen a number of cryptocurrencies fall victim to 51% attacks. Verge, Bitcoin Gold, ZenCash, and Electroneum are just a few coins that have been targeted, resulting in a total equivalent theft of $5 million (not to mention the subsequent loss in market value of the coins). Read more...

Evolving cellular automata to solve problems, part 2

[ programming ]

We will be picking up where the previous post left off. As a brief summary, we are attempting to replicate the results of Evolving Cellular Automata with Genetic Algorithms (Mitchell, Crutchfield and Das 1996), dealing with the density classification task for 1D binary cellular automata (CAs). To put it simply, we are trying to design a ruleset such that the final configuration of a cellular automaton after M iterations is either all 1s or all 0s depending on which class was more common in the initial state. The caveat is that each cell in the universe can only make its decision based on the three neighbours to the left and right. Read more...

Evolving cellular automata to solve problems, part 1

[ programming ]

Recently I finished reading Complexity: A Guided Tour, by Melanie Mitchell, which reminded me a lot of Gödel, Escher Bach (indeed, the book is dedicated to Douglas Hofstadter). It has reminded me that emergence is an incredibly fascinating concept – simple individual units somehow coming together to result in complex behaviour that cannot really be explained in terms of the components. In this post, we analyse the emergent behaviour of a cellular automaton and attempt to use it to solve a simple problem. Read more...

Classifying financial time series using Discrete Fourier Transforms

[ quant ]

A financial time series represents the collective decisions of many individual traders; it seems reasonable to me that the nature of these decisions may differ based on the underlying asset. For example, a company with a higher market cap may be more liquid, and subject to larger individual buy/sell orders including institutional investment. Thus, there is a case to be made that information such as the market cap of a company should be ‘encoded’ into its price movements. While these characteristics may be difficult to pinpoint on a chart, in principle it may be possible for a machine learning algorithm to find statistical relationships between the time series and the market cap of the company. This post will investigate that claim. Read more...

DIY MachineLearningStocks

[ machine-learning ]

I recently released a machine learning stock prediction project on GitHub, unimaginatively named MachineLearningStocks. It is a project that I’ve put quite a lot of time into, and is in fact a simplified version of a system that I’ve been using to live trade. This post doesn’t really offer anything on top of the existing readme, but I figured it would be good to have a copy (with some minor changes) here as well. Read more...