Deep LSTM with Reinforcement Learning Layer for Financial Trend Prediction in FX High Frequency Trading Systems

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.

Deep LSTM with Dynamic Time Warping Processing Framework: A Novel Advanced Algorithm with Biosensor System for an Efficient Car-Driver Recognition

“…The LSTM cell (see Figure 9 detail) is able to select what information to discard or store. In order to produce effective results in real applications, this selective method requires three different mechanisms to read, store, and discard information by taking advantage of specific vectors called "gates" [23,24]. The mathematical model of the used LSTM cell is the following:…”

“…The author is bringing the algorithm described, in this study, into microcontrollers designed and certified for the automotive industry. Specifically, to manage the sampling and preprocessing part of the PPG signal by using devices of the SPCxx family of 32-bit automotive microcontrollers series produced by STMicroelectronics specifically for the ADAS sector [24] and equipped with ADC and ARM core(s) for implementing the preprocessing pipeline, as described in Section 2. The DTW technique and deep learning have been covered by the ST Accordo5 microcontroller [25,26].…”

“…..n; x = (HP, LP); y = (HP, LP) ∀ n, m ∈ N + (14) Figure 8 shows an example of the DTW processing through the SKL metric between a signal patterns of the car-driver PPG signal (coming from biosensing device on the steering) and the corresponding signal pattern generated from the reference RD-M: Figure 8 shows an example of the DTW processing through the SKL metric between a signal patterns of the car-driver PPG signal (coming from biosensing device on the steering) and the corresponding signal pattern generated from the reference RD-M: The collected setup of similarity values ( ) are used as input for the deep long short-term memory (LSTM) model [20][21][22][23][24] described in the next subsection.…”

“…The proposed deep learning pipeline is depicted in Figure 9. The collected setup of similarity values δ k xy (k) are used as input for the deep long short-term memory (LSTM) model [20][21][22][23][24] described in the next subsection.…”

Machine Learning for Quantitative Finance Applications: A Survey

“…A recent work is [49], in which the author implemented an algorithm based on supervised DL and reinforcement learning algorithm. The main goal is to forecast the short-term trend in the currency FOREX (FOReign EXchange) market with the aim to maximize the return of investment in a high-frequency trend (HFT) algorithm.…”