Deep Moving Average
Every indicator has its advantages and disadvantages. Trending ones show good signals during a trend, but lag during a flat. Flat ones thrive in the flat, but die off as soon as a trend comes. All this would not be a problem, if it was easy to predict when a flat changes to a trend and when a trend changes to a flat, but in practice it is an extremely serious task.
What if you develop such an algorithm, which could eliminate an indicator's flaws and enhance its strengths? What if such an algorithm could improve the operation of a trend indicator during a flat, but at the same time increase the efficiency during a trend, and fix the signals of a flat indicator during a trend and perfect them during a flat?
«Deep» is that very algorithm, which enhances the advantages of an indicator and minimizes its disadvantages. In short, this algorithm makes an indicator better. In an attempt to merge neural networks with a standard indicator, to my surprise, I received quite interesting results.
On the concept of «Deep».
The specified task, due to its non-reproducibility and complex regularity, are best soled by non-linear algorithms. Neural networks are a very versatile and powerful tool, which allows to achieve a lot, if the task is set correctly and the solution is formed reasonable. The algorithm is based on this very tool.
In fact, the algorithm measures the optimal periods of a moving average on all area, depending on the state of the trend and the flat. On a flat area the algorithm adapts the period of the moving average towards the flat, on a trend area - towards the trend. By increasing the depth of the "Deep", you can increase the flexibility of the adaptive properties of the algorithm.
The architecture of the network and the heuristic search algorithm were designed specifically for this task. Multilayered structure and the amount of neurons in a layer are regulated dynamically, the user only needs to specify the maximum number of neurons in a layer, the maximum size of a layer and the maximum number of layers.
- Device - device to calculate the indicator. Available options: CPU or GPU.
- Graphic objects prefix name - name prefix of the graphic objects (for example, the panel name).
- TimeFrame - timeframe.
- Period - period of the moving average.
The "Deep" algorithm
- Deep - needed to regulate the depth of the period of the moving average.
- Deep Smoothing - smoothing of the result.
- Deep Sensitivity - algorithm sensitivity.
- Spread in points - spread size for fine-tuning the heuristics.
- Max: Number of Sensors - the maximum number of sensory neurons.
- Max: Layer Size - the maximum number of neurons in a layer.
- Max: Number of Layers - the maximum number of layers.
- Max: ratio of signal deformation - the coefficient is used for deformation of signals.
- Max: Signal range - signal changing range.
- Signal digits - accuracy of the signals.
- Power - the power of the calculations, set in percentage from 1 to 100.
- Number of Bars - the number of bars for calculations.
- Signal mode - signals mode.
- Q Method - adaptivity calculation method. These algorithms are used to improve the adaptive characteristics of signals.
- Show Mode - indications display mode.
- Up Arrows Code - up arrows code.
- Dn Arrows Code - down arrows code.
- Arrows Vertical Shift (in points) - vertical offset of arrows.
- Alerts? - display a dialog box.
- Play Sound? - play an audio file.
- File Name To Sound Play - name of the audio file.
- Send To Mail? - send an email.
- Mail Header - email header.
- Notifications? - sends push notifications to the mobile terminals.
- Panel? - display the panel.
- Starting X - starting horizontal position (in pixels).
- Starting Y - starting vertical position (in pixels).
- Size multiplier - panel size multiplier.
- Color - panel background color.
- Transparent % - panel transparency (from 10 to 100).
- Border Color - panel border color.
- Slider color - slider color.
- Txt color - main text color.
- Txt 2 color - other text color.
Now you can select the device for the indicator to use: CPU (central processing unit), GPU (graphics processing unit).
2) Added: MTF.
3) Added: arrows for signals.
4) Added: multicolored lines.
5) Added: alerts, sounds, notifications.
6) Added: graphical control panel on the chart.
Now you can:
- monitor certain information;
- adjust the calculation power (move the slider to do this);
- move the control panel on the chart.
7) Improved: heuristic algorithm.
8) Improved: architecture of the neural network.
9) Added: more methods for calculating signals and adjusting the heuristic algorithm.
10) Added: more input parameters for advanced settings.
11) Fixed all detected bugs.
12) More stable operation.
13) Optimized resource consumption.