Trading rototes-using neural networks, machine learning methods for the forex market

This article discusses the possibility of using neural networks to create highly efficient trading robots for the Forex currency market, and examines the possibility of using neural networks and machine learning methods in trading robot algorithms. The existing Fractal neural network is considered as an attempt to create a prototype of a neural network. The estimation of the network operation is given using the mean-square error prediction index, the percentage of correctly predicted and missed fractals.