Configuring Neural Network Models

TradingSolutions comes with several general neural network models that you can use to develop predictions. By default, the program automatically selects an appropriate pre-configured model for the prediction being made. However, there may be times when you want to select a different model or modify the pre-configured model.

Creating Predictions Using General Models

By default, TradingSolutions selects an appropriate pre-configured model for the type of prediction you are making. If you would like to use a general model instead of a pre-configured one, select Use a general model and configure it now from the Predict a Value Wizard: Select Options page while you are creating a prediction. Selecting this option will cause the Next button to proceed to the Configure Model page where you can select and configure a general model. Additional help with configuring models is below.

&  For more help with the Predict a Value Wizard, see the help for the Predict a Value Wizard.

Modifying Pre-Configured or General Models

Once a predicted field has been created using either a pre-configured model or a general model, the model can be modified using the Modify Field Dialog: Prediction Model page. Changing any of the options for the model will cause the model to be retrained automatically to account for the new changes. Additional help with configuring models is below.

&  For more help with the Modify Field Dialog, see the help for the Modify Field Dialog.

Selecting a Neural Model

TradingSolutions comes with several general neural network models. These are broken into two basic types: static neural networks and dynamic neural networks.

Static neural networks train and predict using only current input information. This makes them good for classification problems in that they treat each set of inputs as a separate case. Static networks can also be used for time-series predictions by providing multiple historical samples as inputs. Static neural networks include multilayer perceptrons (MLP), modular networks, and Jordan/Elman networks.

Dynamic neural networks train and predict using current input information, as well as a memory of recent input values and other training values. This makes them good for time-series predictions, such as price predictions, since they automatically maintain a memory of recent information to apply against the current information. Dynamic neural networks include time-lag recurrent networks and recurrent networks.

Most of the processing of a neural network takes place in its hidden layers. All of the neural models in TradingSolutions can have one or two hidden layers. Having fewer hidden layers simplifies a neural model, allowing it to train more easily. Having more hidden layers allows a neural model to learn more complex patterns, but makes it more difficult to train.

Each general neural model in TradingSolutions has a list of characteristics, or subtypes, that can be selected from in order to further refine the model. These primarily vary how the various components of the model are connected, but can also be used to select different types of memory in dynamic networks.

Modifying Individual Neural Network Components

After selecting a neural model on the Predict a Value Wizard: Configure Model page or the Modify Field Dialog: Prediction Model page, you can further modify the neural model by pressing the Advanced Topology Settings… button. This will display the Advanced Topology Settings Dialog, from which you can customize the processing elements, memory depths, and learning rates of individual components. By default, TradingSolutions will automatically maintain the best estimates for all of these values.

&  For more help with this dialog and the individual components, see the Advanced Topology Settings Dialog help.

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