Modify Field Dialog: Training Settings

The Modify Field Dialog allows you to modify the properties of a previously created field. This page allows you to view or modify the settings associated with training or optimizing this prediction.

Ä    Note: Fields that are currently being used by the Solution Service cannot be modified.

&  For help with predictions, see Predicting and Modeling Financial Data.

Re-optimizing this Prediction

The inputs and settings associated with this prediction can be optimized for better performance. The following settings are available:

þ    Re-optimize neural network inputs and settings on save.

This option causes the prediction to be optimized from its current state after the OK button is pressed. Any current settings or training will be lost. For fields created for entire groups, this prediction will automatically be optimized for any new data added to the group. To re-optimize the prediction for the entire group, uncheck and re-check this option.

Ä    Note: If optimizable functions were used to create inputs during a previous optimization, TradingSolutions will offer to remove these previously created fields so that they do not interfere with trying new optimization values.

Ä    Note: If this is a field defined for an entire group, optimization cannot be turned off for this field.

Ä    Note: If re-optimization is selected, it cannot be deselected after leaving this page except by pressing the Cancel button to leave this dialog.

p    Optimization Settings…

This button will display the Training Optimization Settings Dialog which allows you to modify the options used for optimizing this prediction.

Modifying the Training Data

The data range associated with a prediction is used for several different things. Part of the data is used for training the neural network model. Part of the data is used as a validation step to make sure the training is improving the results. And, part of the data is left out of the training process to be used for only for testing. The ranges are also used for checking the results of the optimization.

¨    Training Range

This setting displays the current data range being used for this prediction. It can be used to select from typical settings for the training range. Pressing the Training Range… button will display the Modify Optimization Range Dialog, which allows greater control over the date range.

There are no definitive rules for how much data should be used for training a prediction. Including more data is useful for improving results since it provides additional examples for training. However, older financial data may have been produced under different market conditions than more recent data, causing the training to focus on outdated or overly generalized principles.

Ä    Note: For predictions being defined for an entire group or predictions that use external data as inputs, the data range is limited to the common date range for all of the data being used. For example, if the group for which you are defining a prediction has a data series with only one year of data, the prediction will only be able to use one year of data, even if the other data series in the group all have more data.

You can increase a limited data range by either importing more data into the shorter data series, or removing the data series from the prediction. You can quickly determine the first date available in your data series by adding the first date as a display field in the Portfolio View.

&  For help with display fields, see Using Display Fields.

Exporting the Training Data for use in NeuroSolutions

NeuroSolutions is general purpose neural network software from NeuroDimension, the makers of TradingSolutions. It can be used to create custom neural networks for use in TradingSolutions with the addition of the Custom Solution Wizard add-on product.

To export the selected training set into files that can be used from within NeuroSolutions, press the Export Training Data for use in NeuroSolutions… button. This will display a file selection dialog labeled Export Training Data As. This dialog allows you to specify the name of the main file to export the data to. Once you have selected a file name and directory, press the Save button.

&  For help with the file selection dialog, see the help for the File Selection Dialog.

The data for the training set will be saved in the file name selected. If a cross validation set is allocated, the cross validation set will be saved in the same file name with "_CrossVal" added. If a testing set is allocated, the testing set will be saved in the same file name with "_Testing" added.

Ä    Note: Field names with characters that cannot be handled by the NeuroSolutions file component will automatically be converted for use in NeuroSolutions.

Modifying the Training Settings

The settings associated with terminating the training can also be viewed of modified from this page.

p    Training Settings…

This button displays the Modify Training Settings Dialog, where you can modify the settings used for training the neural network.

What Do I Do Next?

If you are finished updating the properties of a previously created field, press the OK button to save your changes or select another property page. If you would like to exit from this dialog without performing any changes, press the Cancel button.

Additional Property Pages

The Modify Field Dialog has many different property pages that will be displayed as is appropriate for the type of field being modified. For information on the other property pages available, see the help for the Modify Field Dialog.

How Did I Get Here?

The Modify Field Dialog appears when you select to modify or analyze the selected field from the Modify Data Series Dialog or the Modify Portfolio/Group Dialog. It is also displayed when you select Modify Field… from the context menu for a field in a chart or spreadsheet.