This page gives you access to a serie of short animated tutorials that explains how to use the SAFIR-Xp software

 


 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 


 

 

 

 

 

 

 

 

 
   Tutorials for

 

Tutorial 1: - Step by step example

The search for fuzzy trading systems takes place in a workspace.To create a new workspace: Menu File/New workspace or icon
A splitted window associated to this workspace is displayed.

 

Tutorial 2-1: Choose the indicators

In this example we suppose that indicators are not part of the data files. Built-in indicators are used.
To add built-in indicators : Move the mouse to the Configuration frame, right click and select the popup menu Built-in indicators, then the Add command.

Tutorial 2 -2 :Select the indicators you want to use for this configuration

 If you look at the bottom of the indicator configuration frame, you can see that a tab named Conf1 has been created, and that all the rows in the table have the "Use it" cell set to off (red cross). This means that :

  • you must choose among all the indicators those you want to investigate first. The best results are obtained with 4 to 6 indicators, delta ones included.

  • you will be able to create other configurations (see Tutorial 9b) and compare the results in the solution summary view.

Tutorial 3-Add a data file to the Explore portfolio

 We are using data files created by the Save command of TS6 Data Window. The extension of these files is .txt. For each bar, they contain the following information:

§         Date §         Time§         Open §         High  §         Low §         Close.
The other fields are ignored by SAFIR-X.

Tutorial 4 -Control the Train/test ratio.

 The data set contained in the es.d file will be used by SAFIR-X to create fuzzy inference systems (FIS), each of them will be the engine of the fuzzy trading systems. SAFIR-X will use the first part of the file to build its knowledge base (train) and the last part to validate the FIS (test).
The default train/test ratio is displayed in the upper info bar with the number of bars for training and for testing purposes. It is around 50%. It is also materialized by a vertical dashed line in the Prices and criteria chart view.Typically 2000 - 3000 bars are enough for the training part.

Tutorial 5 - Control the zigzag retracement factor

  This figure is really important because it determines the amplitude of the zigzags, which are the theoretical positions that SAFIR-Xp will attempt to learn.  The default value is 1%.This information is displayed in the upper info bar (PercentZ): To look at the zigzags, keep the data file selected and click the right mouse button above it in the portfolio frame. Run the Show Target command.

Tutorial 6 - Control the price options

  Before starting a search for trading systems, you must check the price settings
(point value, transaction cost, deposit or fixed amount..). These informations are also displayed in the upper info bar.
 In this example the parameters are correct because they are associated with the prefix of the data file
(in this case E Mini, prefix es.d). This can be defined in the options Prices tab.
It is possible to locally modify  these values.  

Tutorial 7- Search for fuzzy trading systems

 Now that all settings have been verified we are ready to start the search. The Explore command starts the process.

Tutorial 8 - Add unseen data to the check portfolio

 It is crucial to validate the fuzzy systems found during the previous step on unseen data before using them in real market conditions.
 In this example we validate the systems built with a future indice on Nasdaq stocks.

We apply the same steps to add data to the check portfolio:

  • Select the Check portfolio icon  in the portfolio frame,

  • Run the Add files command. Keep the CTRL key down  to make a multiple selection,

  • Check the price options displayed in the Upper info bar.

Tutorial 10:- automated sequencing of tasks

As you can notice it, arbitrarily fix the main parameters of the search does not give good results straight off. It may be necessary  to make many trials. Here is a way to speed up the process.

First, let's try another configuration of indicators. Use the Validate as item of the configuration frame menu to create a copy of the current configuration. Then uncheck the Use it cell of Slowk(5) and Adx(10) and check Slowk(25) and Rsi(20). Since the grid has been edited, use the Validate command to confirm the changes. The new set of indicators of Conf 2 is Slowk(15), Slowk(25), Rsi(20) and the deltas of Slowk. 

Tutorial 11 - Automatic zigzag setting

  Rather than fixing a retracement percentage for the zigzags we let SAFIR-X computes the most adequate value.
 The command  (Z+Explore+Check) computes the zigzags according to the length of the indicators, performs a search for systems, then a validation. Another similar command applies the same process to all the configurations of a workspace (Tools menu).  

Tutorial 12: -Automated search for train/test periods

 In this example we highlight one of the most powerful capability of SAFIR-Xp. More than the choice of indicators or the zigzag definition, the selection of the training period is really crucial to make SAFIR-Xp build a reliable knowledge base. However, in the previous examples the training period was always the first part of the data, even if it was not the most adequate.

 The principle of the Search for train/test periods is a scan of the data through a moving window. The size of this window is typically the same as the one used during Explore (about 1000 bars x number of indicators). 

At each step, SAFIR-Xp evaluates:

§         Its capability to learn on the train period,

§         Its capability to generalize on the test period,

§         And its capability to generalize on the remaining part of the data file.

The moving window is then shifted by an offset. You can see the window moving in the Criteria and prices view. If the test is positive the train part is redrawn in red color, else in yellow. The test part is redrawn in white color. 

At scanning completion, the successful periods are sorted according their result on the whole Explore file or on the Check portfolio. 

The best results give place to the creation of new workspaces. Each of them receives in its Explore portfolio the train/test interval defined in the previous step. It is possible to transfer the remainder of the original data file in the check portfolio of the new workspaces. It is also possible to transfer the original Check portfolio.

Exploration parameters, indicators, and zigzag settings of the original files are copied.
For each new workspace, SAFIR-Xp runs an Explore and a Check.

 When the command completes, you have at your disposal new workspaces with solutions. If there are good results, you can save, create new configurations, modify the parameters, make other checks or export some systems. If results are bad, do not hesitate to kill the workspace.

 All the parameters and the options of the analysis can be set in a dialog box.



This is the end of this short introduction to SAFIR-Xp.
You are strongly invited to read the on line user guide before going further.

Try to reproduce this workspace before using your own settings and data files.
Do not expect to find good results at first time.
You will have to do many trials before finding a good combination : train/test period - zigzag - indicators.

We hope you will enjoy this software and find valuable trading systems with it.

 

   -Safir-Xs free trial offer :

  2- TradeStation 8 low cost trial offer

  

TradeStation is recommended to properly test our products, althought you could use ASCII data files.

You may test TradeStation 8 for  25$ during  30 days.

No limitation,  works realtime and  give a full access to the huge TradeStation intraday and daily  database.

More information on this special offer  HERE

2

 

 


Info Box 1

Click on the Title associated to each tutorial part and follow the explanation on the screen

 

Info Box 2

The most important tutorial is the latest (#12).

It highlights the  full automation of the process