ROBOT ADVISOR - STOCHASTICS + ARTIFICIAL INTELLIGENCE (neural network)
The market is constantly changing, and old ideas periodically outlive themselves. But, if the problem cannot be solved by the traditional method, a non-standard approach, for example, neural network analysis, comes to the rescue. This approach is used by the adviser with the simplest name Robot, which combines traditional technical analysis with the beginnings of artificial intelligence.
Because This is a neural network robot, it has the ability to work in any currency pairs and markets. Learning the principles of the dynamics of a given asset does not limit it in terms of timeframe and time of work. Therefore, you can use it both in long-term trading and in scalping. The difference is only data for training.
Timeframe: any
Currency pairs: any
Trading time: around the clock ( 24 )
And although the adviser does not have full-fledged artificial intelligence, the use of such an algorithm offers several advantages compared to the traditional (manual) selection of logical conditions.
First, it is the flexibility of the conditions themselves. All that you specify at the beginning: the type and number of input parameters, but, by default, the adviser does not yet know what to do with these parameters. Only in the process of optimization (training), the adviser acquires a certain picture of the market and can predict its movement in the future, based on its past experience.
Secondly, it is the possibility of quick retraining. If the market has changed and the old patterns have lost their relevance, you only need to re-optimize the values of the scales, and then (in theory) the robot will again work profitably.
Based on the optimization results, the best option was obtained (taking into account profit / drawdown) with the following parameters:
Step - 5
x1 - 0
x2 - 70
x3 - 150
x4 – 160
Do not use aggressive money management.
Robot is a practically universal adviser that, among other things, can be easily adapted to any market situation. The mult parameter is responsible for the lot multiplication in the sequence, which allows using both aggressive and more conservative approaches to trading (for a fixed lot, set the value to 1.0).
However, this is not the Grail at all, as it may seem at first glance - Robot requires constant attention, because once having “learned” how to work on one version of the market movement, the adviser will simply follow the familiar market paradigm. When the situation changes, it may start unexpectedly for the owner to lose money. In terms of efficiency, such an approach is generally similar to manual periodic selection of conditions for advisers, but its main advantage is considerable time saving for the trader, and the result may even outperform more “advanced” strategies.
Therefore, in order to ensure that the results remain predictable and satisfactory, periodically re-adapt the weights, then the robot will always deal with the current market picture.
The market is constantly changing, and old ideas periodically outlive themselves. But, if the problem cannot be solved by the traditional method, a non-standard approach, for example, neural network analysis, comes to the rescue. This approach is used by the adviser with the simplest name Robot, which combines traditional technical analysis with the beginnings of artificial intelligence.
Because This is a neural network robot, it has the ability to work in any currency pairs and markets. Learning the principles of the dynamics of a given asset does not limit it in terms of timeframe and time of work. Therefore, you can use it both in long-term trading and in scalping. The difference is only data for training.
Timeframe: any
Currency pairs: any
Trading time: around the clock ( 24 )
And although the adviser does not have full-fledged artificial intelligence, the use of such an algorithm offers several advantages compared to the traditional (manual) selection of logical conditions.
First, it is the flexibility of the conditions themselves. All that you specify at the beginning: the type and number of input parameters, but, by default, the adviser does not yet know what to do with these parameters. Only in the process of optimization (training), the adviser acquires a certain picture of the market and can predict its movement in the future, based on its past experience.
Secondly, it is the possibility of quick retraining. If the market has changed and the old patterns have lost their relevance, you only need to re-optimize the values of the scales, and then (in theory) the robot will again work profitably.
Based on the optimization results, the best option was obtained (taking into account profit / drawdown) with the following parameters:
Step - 5
x1 - 0
x2 - 70
x3 - 150
x4 – 160
Do not use aggressive money management.
Robot is a practically universal adviser that, among other things, can be easily adapted to any market situation. The mult parameter is responsible for the lot multiplication in the sequence, which allows using both aggressive and more conservative approaches to trading (for a fixed lot, set the value to 1.0).
However, this is not the Grail at all, as it may seem at first glance - Robot requires constant attention, because once having “learned” how to work on one version of the market movement, the adviser will simply follow the familiar market paradigm. When the situation changes, it may start unexpectedly for the owner to lose money. In terms of efficiency, such an approach is generally similar to manual periodic selection of conditions for advisers, but its main advantage is considerable time saving for the trader, and the result may even outperform more “advanced” strategies.
Therefore, in order to ensure that the results remain predictable and satisfactory, periodically re-adapt the weights, then the robot will always deal with the current market picture.
