Reply to thread

The great thing about web data is there is a ton of it.  We also added the CRM (leads) and DMS (sales and ROs) data as nodes.  This isn't a static model, rather a trained data set using machine learning (python to R).  The prediction allows you to determine the next node probability and that definitely has use cases.  There are also others.  For example we came up with a concept called marketing resiliency.  For this consider an example of a power grid and sub stations.  In order to prevent black outs energy companies create redundancies so the electricity can path around a substation that goes out.  Same goes for marketing.  If you remove a node more traffic paths through the other nodes.  Therefor each carries more of the weight creating a higher risk factor.  Basically to many eggs in one basket.

In terms of error testing that is part of the model validation and input feature tuning.  For that process I believe (if I can recall) we used an out of bag testing procedure.