Cluster Indicators make good inputs to a neural network. (For the neural net enthusiasts, this creates a paradigm much like the popular classic Radial Basis Function neural nets, except in the NeuroShell Trader Professional or NeuroShell DayTrader Professional, your clusters don't all have to be based on the same inputs, and in fact can be optimized! There was also a paradigm called Counter-propagation that was similar to feeding the Cluster Indicators into a neural net.)

To use Cluster Indicators as inputs to neural nets, just specify them as inputs. You can use them as inputs to other add-ons too, such as Adaptive Net Indicators, Neural Indicators, and Adaptive Turboprop2. Note that if you are optimizing neural network inputs, each Cluster Indicator and all of its inputs will be optimized as well. So there might be quite a bit of optimization going on if you use too many Cluster Indicators.

Inputs to the Cluster Indicators are scaled internally to bring them all into the same range of variation before computing the distance. There is no need to perform any additional pre-processing of inputs.

Note:  We believe that using Cluster Indicators with fewer inputs will more likely result in models that are more robust when applied to future data.