Abstract
FOREX (Foreign Exchanges) is a 24H open market with an enormous daily volume. Most of the used Trading strategies, used individually, are not providing accurate signals. In this paper, we are proposing an automated trading strategy that fits random market behaviors. It is based on neural networks applying triple exponential weighted moving average (EMA) as a trend indicator, Bollinger bands as a volatility indicator, and stochastic RSI as a momentum reversal indicator to prevent false indications in a short time frame. This approach is based on trend, volatility, and momentum reversal patterns combined with a market adaptive and a distributed multi-layer perceptron (MLP). It is called channeled multi-layer perceptron (CMLP) that is a neural network using channels and routines trained by previous profit/loss earned by triple EMA crossover, Bollinger Bands, and Stochastic RSI signals. Instead of using classic computations and Back-propagation for adjusting MLP parameters, we established a channeled multi-layer perceptron inspired by a multi-modal learning approach where each group of modalities (Channel) has its K_c That stands for a dynamic channel coefficient to produce a multi-processed feed-forward neural network that prevents uncertain trading signals depending on trend-volatility-momentum random patterns. CMLP has been compared to Multi-Modal GARCH-ARIMA and has proven its efficiency in unstable markets.
Highlights
Financial markets are where securities trades occur, including the forex market, stock market, bond market, and derivatives market
Our approach is based on channeled multi-layer perceptron, in other words, building a feed-forward neural network that has a channel for each features group as follows: A
The back-testing execution is done on a machine with Ubuntu 18.04 as an operating system and Docker containers for worker nodes to provide a simulated aspect of distributed computing
Summary
Financial markets are where securities trades occur, including the forex market, stock market, bond market, and derivatives market. Machine learning is the best way to build a robust algorithmic trading platform by retrieving historical market data, selecting efficient features training machines for future market movement prediction[1], [4]–[6]. Traders use several technics to have an accurate expectation on future trending. The well-known technic is moving average; it has three famous alternatives; the first is Simple Moving Average[1], [15], [16], it uses the last N values average. An enhanced version of moving average is exponential weighted moving average[17], [18]; instead of assigning the same weight to all values, EMA gives more weight to last values This technique has evolved, and traders use a triple EMA with different selective periods to predict market prices accurately. Momentum that has a famous method, the Stochastic Relative Strength Index that shows the market position reversal[21]–[23]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Advanced Computer Science and Applications
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.
