Abstract
High-frequency trading is a method of intervention on the financial markets that uses sophisticated software tools, and sometimes also hardware, with which to implement high-frequency negotiations, guided by mathematical algorithms, that act on markets for shares, options, bonds, derivative instruments, commodities, and so on. HFT strategies have reached considerable volumes of commercial traffic, so much so that it is estimated that they are responsible for most of the transaction traffic of some stock exchanges, with percentages that, in some cases, exceed 70% of the total. One of the main issues of the HFT systems is the prediction of the medium-short term trend. For this reason, many algorithms have been proposed in literature. The author proposes in this work the use of an algorithm based both on supervised Deep Learning and on a Reinforcement Learning algorithm for forecasting the short-term trend in the currency FOREX (FOReign EXchange) market to maximize the return on investment in an HFT algorithm. With an average accuracy of about 85%, the proposed algorithm is able to predict the medium-short term trend of a currency cross based on the historical trend of this and by means of correlation data with other currency crosses using techniques known in the financial field with the term arbitrage. The final part of the proposed pipeline includes a grid trading engine which, based on the aforementioned trend predictions, will perform high frequency operations in order to maximize profit and minimize drawdown. The trading system has been validated over several financial years and on the EUR/USD cross confirming the high performance in terms of Return of Investment (98.23%) in addition to a reduced drawdown (15.97 %) which confirms its financial sustainability.
Highlights
The key to correctly identifying market trend is to correctly estimate both medium-term and long-term trends
These factors, more often than not unpredictable, generate a certain level of uncertainty and non-predictability which obviously will have a greater impact in the long term and are more contained in the short term if the trading system policy provides appropriate financial compensation or loss-cutting algorithms based on prudent use of dynamic stop-losses
A similar classification pipelines have been used effectively by the author in appropriately classifying both signals and images albeit in different areas than the financial one here described [27,28,29,30,31]. This confirms that the approach of cascading a SoftMax block with classifier to a deep network capable of extracting features from input data (LSTMs, convolutional neural networks, auto-encoders, etc.) is certainly robust as well as performing with regard to discriminative capacity [32]
Summary
The key to correctly identifying market trend is to correctly estimate both medium-term and long-term trends. To the above we add the observation that the foreign exchange market presents strongly non-linear and non-stationary cross dynamics influenced by macroeconomic factors, national and international monetary policies, military conflicts, etc These factors, more often than not unpredictable, generate a certain level of uncertainty and non-predictability which obviously will have a greater impact in the long term and are more contained in the short term if the trading system policy provides appropriate financial compensation or loss-cutting algorithms based on prudent use of dynamic stop-losses. The result of the survey in [10] confirmed that the best trading strategy based on the use of deep neural network is the ones which shows high predictive accuracy in low volatility market, as it can help investors on reducing the risk while obtaining satisfactory returns. RL pipeline is able to reproduce around 80% of the well-performing trading decisions both in training and validation sessions
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.