Requires a network of training (optimization)!
Professional robot, which implemented trading strategy using neural networks. Used fully connected multilayer feedforward network MLP (multilayer perceptron).
The ability to learn is the main feature of the brain. Artificial neural networks for learning refers to the process configuration of network architecture (structure of connections between neurons) and the weights of synaptic connections (influencing factors signals) to effectively solve the problem. Typically a neural network is trained on a sample (historical data). As the learning process that takes place on some algorithm (used for training optimization genetic algorithm), the network should get better (better) to respond to input signals.
It remains only to check how well-optimized settings allow you to make a prediction for the future. What method is used phased test results. Example, with the settings to optimize the (training) is provided in the discussion.
At the beginning of the current bar is analyzed indicators RSI, SSI, WPR. Results from 10 bars of each of the indicators fall to the input of the neural network. The weighting factors are formed separately for purchases and sales. The network is trained on the data of the indicators and, depending on the signal level at the output of the neural network may be 4 teams (with TypeDual = true): to open / close the buy order to open / close the sell order. And depending on this will open a BUY or SELL and keep this deal will go until the closing signal from the network. There is also a mode of operation of the neural network with two outputs (with TypeDual = false): the first – the entrance to the purchase of automatic exit from the market, the second input to the sale with automatic access to the purchase.
Expert correctly handles the error and works reliably with a capital of 100 USD. The expert uses the basic concepts: breakeven, trailing stop, stop loss and take profit, as well as the closure on the opposite signal, closing the signal and the proper risk calculation.
- 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.
- 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.
The following fields relating to the RSI indicator, similar to all subsequent indicators:
- EnabledRSI – Activation of the indicator.
- k1_RSI_long – coefficient of influence of light on the sum signal for a long position.
- k1_RSI_short – coefficient of influence of light on the sum signal for a short position.
- Period1_RSI – indicator period.
- Layer_1AL – Field 1 to the neural network configuration for a long position.
- Layer_1BL – Field 2 for the neural network configuration for a long position.
- Layer_1AS – Field 1 to the neural network configuration for a short position.
- Layer_1BS – Golf 2 for neural network setup for a short position.
Neural network 2 Moving Averages Neural network Adviser on two moving averages with learning mode. Educate your adviser on these examples and make profit…
Multi Expert System TRADING WAY Capabilities: Terms of expert inputs and outputs generated by the indicator MultiSignals_PCH , which can be downloaded…
MACD 3TF VI Martingale Expert MACD 3TF VI Martingale from the series “Trading systems with increased volume position.” Here is a brief description. A…
- Stop close only orders