Hybrid Forex prediction model using multiple regression, simulated annealing, reinforcement learning and technical analysis

Hana Jamali, Younes Chihab, Iván García-Magariño, Omar Bencharef

Abstract


Foreign exchange market refers to the market in which currencies from around the world are traded. It allows investors to buy or sell a currency of their choice. Forex interests several categories of stakeholders, such as companies that carry out international contracts, large institutional investors, via the main banks, which carry out transactions on this market for speculative purposes. One of the most important aspects in the Forex market is knowing when to invest by buying, selling, and this through the recorded trend of a currency pair, but given the characteristics of the Forex market namely its chaotic, noisy and not stationary nature, prediction becomes a big challenge for traders when it comes to predicting accuracy. This paper aims to predict the right action to be taken at a certain moment through the development of a model that combines multiple techniques such multiple regression, simulated annealing meta-heuristics, reinforcement learning and technical indicators.

Keywords


Forex; Prediction; Regression algorithm simulated annealing; Reinforcement learning; Technical indicators

Full Text:

PDF


DOI: http://doi.org/10.11591/ijai.v12.i2.pp892-911

Refbacks

  • There are currently no refbacks.


View IJAI Stats

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.