AnalyzerNeuralNetwork
Professional robot, which implemented trading strategy using neural networks. Used fully connected multilayer feedforward network MLP (multilayer perceptron). BotNeyron development project. Externally, the expert user is not very different from its predecessor, it changed the internal configuration of the neural network, which is aimed at forecasting over longer periods of time. Added options for MonoInversion, which simplifies the internal structure of the neural network. Examples of settings for different structures in the form of files with the extension ".set" provided in the discussions. All information relating to the previous expert BotNeyron, suited to this expert.
Note:
Expert at work uses accounting positions in the netting mode (one character can have only one position). Expert does not work with independent accounting positions (hedging, when one character can be several positions). When tested on a demo account you need to choose an account without hedging. Also, consider this fact when opening an account for the real work.
Options:
- PeriodWork - working period of the expert system.
- Risk - The risk (calculation of the lot of the deposit).
- LotRounding - Rounding out the lot.
- Deviation - slippage.
- Sleeps - waiting before retrying the order opening.
- StopLoss - Stop-loss.
- TakeProfit - Take Profit.
- PeriodTrailing - Period to control the trailing stop.
- TrailingBreakeven - zero-loss level.
- TrailingStart - Trailing start.
- TrailingStop - Trailing Stop.
- PeriodTrailingStep - step period trailing stop.
- ProhibitNewSeries - Allows you to close the series and do not open a new one.
- WorkOpenLong - Allows you to open a long position.
- WorkOpenShort - Allows you to open a short position.
- WorkCloseLong - Allows you to close long positions.
- WorkCloseShort - Allows you to close short positions.
- WorkCloseReversLong - Allows you to close a long position when opening brief.
- WorkCloseReversShort - Allows you to close a short position at the opening of the long.
- SignalBar - The main signal bar.
- PeriodSignal - The period in which indicators work, and, respectively, and the neural network.
- TypeDual - Switch mode neural network with 2 or 4 outputs.
- MonoInversion - Simplifies the internal structure of the neural network.
- LevelInLong - entry threshold of the neural network for a long position.
- LevelOutLong - neural network output threshold for a long position.
- LevelInShort - entry threshold of the neural network for a short position.
- LevelOutShort - neural network output threshold for a short position.
- EnabledRSI - Activation of the RSI indicator.
- k1_RSI_long - Coefficient of influence of the RSI indicator on the total signal for a long position.
- k1_RSI_short - Coefficient of influence of the RSI indicator on the total signal for a short position.
- Period1_RSI - RSI indicator period.
- Layer_1AL - Setting up a neural network for a long position on the RSI indicator.
- Layer_1BL - Setting up a neural network for a long position on the RSI indicator.
- Layer_1AS - Setting up a neural network for a short position on the RSI indicator.
- Layer_1BS - Setting up a neural network for a short position on the RSI indicator.
- EnabledCCI - Activation of the CCI.
- k2_CCI_long - Coefficient of influence of CCI on the total signal for a long position.
- k2_CCI_short - Coefficient of influence of CCI on the total signal for a short position.
- Period2_CCI - Period indicator CCI.
- Layer_2AL - Setting up a neural network for a long position on the CCI indicator.
- Layer_2BL - Setting up a neural network for a long position on the CCI indicator.
- Layer_2AS - Setting up a neural network for a short position on the CCI indicator.
- Layer_2BS - Setting up a neural network for a short position on the CCI indicator.
- EnabledWPR - Activation indicator WPR.
- k3_WPR_long - Coefficient of influence WPR indicator on the total signal for a long position.
- k3_WPR_short - Coefficient of influence WPR indicator on the total signal for a short position.
- Period3_WPR - Indicator Period WPR.
- Layer_3AL - Setting up a neural network for a long position on WPR indicator.
- Layer_3BL - Setting up a neural network for a long position on WPR indicator.
- Layer_3AS - Setting up a neural network for a short position on the WPR indicator.
- Layer_3BS - Setting up a neural network for a short position on the WPR indicator.
Settings work when optimizing for Custom parameter:
- kProfit - Corrects the profit impact on the result.
- kDeals - Adjusts the effect of the number of transactions on the result.
- KDD - Corrects the impact of subsidence on the result.
- kSharpe - Sharpe ratio corrects influence on the result.
- kGross - Adjusts the influence of negative positions on the result.
Related posts
ChosenBest Professional robot ChosenBest , in which It implemented a comprehensive strategy for the work set of indicators work in the channels and...
DualDeviationChannel Professional robot, which implements the channel trading strategy StandardDeviationChannel. The signal generated by the rebound...
ENS Pilot ENS Pilot - is Another version of the trading robot from the company Welcome to profit for MetaTrader 5, which combines a finely matched...
Next posts
- COSMOS4U AdMACD EA MT5
- Ferrari EA MT5
- Lazy Locker
No comments:
Post a Comment