1 September 2020 in Quantitative Finance
Systematic trading strategies are algorithmic procedures that allocate assets aiming to optimize a certain performance criterion. To obtain an edge in a highly competitive environment, an analyst needs to appropriately fine-tune their strategy, or discover how to combine weak signals in novel alpha creating manners. Both aspects, namely fine-tuning and combination, have been extensively researched using several methods, but emerging techniques such as Generative Adversarial Networks can have an impact on such aspects. Therefore, our work proposes the use of Conditional Generative Adversarial Networks (cGANs) for trading strategy calibration and aggregation. To this end, we provide a full methodology on: (i) the training and selection of a cGAN for time series data; (ii) how each sample is used for strategy calibration; and (iii) how all generated samples can be used for ensemble modelling. To provide evidence that our approach is well grounded, we have designed an experiment with multiple trading strategies, encompassing 579 assets. We compared cGAN with an ensemble scheme and model validation methods, both suited for time series. Our results suggest that cGANs are a suitable alternative for strategy calibration and combination, providing outperformance when the traditional techniques fail to generate any alpha.
1 January 1994 in Proceedings of the Royal Society of Edinburgh: Section A Mathematics
We consider the following question: given a set of matriceswith no rank-one connections, does it support a nontrivial Young measure limit of gradients? Our main results are these: (a) a Young measure can be supported on four incompatible matrices; (b) in two space dimensions, a Young measure cannot be supported on finitely many incompatible elastic wells; (c) in three or more space dimensions, a Young measure can be supported on three incompatible elastic wells; and (d) ifsupports a nontrivial Young measure with mean value 0, then the linear span ofmust contain a matrix of rank one.
11 April 2022 in IEEE Access
We demonstrate a novel application of online transfer learning for a digital assets trading agent. This agent makes use of a powerful feature space representation in the form of an echo state network, the output of which is made available to a direct, recurrent reinforcement learning agent. The agent learns to trade the XBTUSD (Bitcoin versus US Dollars) perpetual swap derivatives contract on BitMEX on an intraday basis. By learning from the multiple sources of impact on the quadratic risk-adjusted utility that it seeks to maximise, the agent avoids excessive over-trading, captures a funding profit, and can predict the market’s direction. Overall, our crypto agent realises a total return of 350%, net of transaction costs, over roughly five years, 71% of which is down to funding profit. The annualised information ratio that it achieves is 1.46.
1 August 1991 in Communications on Pure and Applied Mathematics
30 December 2021 in IEEE Access
We explore online inductive transfer learning, with a feature representation transfer from a radial basis function network formed of Gaussian mixture model hidden processing units to a direct, recurrent reinforcement learning agent. This agent is put to work in an experiment, trading the major spot market currency pairs, where we accurately account for transaction and funding costs. These sources of profit and loss, including the price trends that occur in the currency markets, are made available to the agent via a quadratic utility, who learns to target a position directly. We improve upon earlier work by targeting a risk position in an online transfer learning context. Our agent achieves an annualised portfolio information ratio of 0.52 with a compound return of 9.3%, net of execution and funding cost, over a 7-year test set; this is despite forcing the model to trade at the close of the trading day at 5 pm EST when trading costs are statistically the most expensive.