Macquarie’s Commodities and Global Markets Group (Macquarie) and UK fund manager, Protean Capital LLP (Protean) have executed the first Quantitative Investment Strategy (QIS) index, that uses signals based on a reinforcement learning (RL) model to inform systematic FX volatility carry trading strategies.
Through its unique market position, Macquarie provides access to a range of specialised investment products, hedging and tailored financing solutions. Macquarie’s Quantitative Investment Strategies (QIS) team tailors systematic products, providing access to commodity, equity, FX and fixed income exposures.
Macquarie leveraged its pioneering technology platform, incorporating state-of-the-art machine learning models, to develop a RL algorithm. The algorithm sizes the number of options to be sold as part of the FX volatility carry strategy. Through these innovative RL techniques, Macquarie was able to improve the strategy’s downside risk profile and risk adjusted returns.
Arun Assumall, Head of Macquarie’s QIS team, says: “The RL model learns market behaviour through trial and error using feedback from its own trading actions during the model training period. The real skill of applying machine learning in this context lies in the training of the model, to ensure it takes the most relevant information and successfully encapsulates the current trading and market dynamics.”
Bob Champney, Managing Partner at Protean Capital, adds: “Protean have been working with Reinforcement Learning techniques to improve client portfolio returns for a number of years but had found it difficult to find a partner bank to provide concrete implementations. Macquarie were the only bank that provided a skill set and platform which enabled Protean to fully benefit from these techniques.”
According to Macquarie, careful application of machine learning and model training, ensures the algorithm is as effective as possible in generating the best trading decisions in live scenarios, and the resulting signals can be easily interpreted by the QIS team. The successful application of RL in volatility strategies paves the way for its wider use in other systematic investment strategies.
