IBM 15 Switch User Manual


 
11
New Features
The Netezza Time Series node analyzes time series data and can predict future
behavior from past events.
The Netezza Generalized Linear model expands the linear regression model so that
the dependent variable is related to the predictor variables by means of a specied
link function. Moreover, the model allows for the dependent variable to have a
non-normal distribution.
IBM SPSS Modeler Premium
The EA Export node is a terminal node that reads entity data from a data source and
exports the data to a repos i t ory for the purpose of entity resolution.
The Entity Analytics(EA) source node reads the resolved entities from the repository
and passes th
is data to the stream for further processing, such as fo rmatting into
a report.
The Streaming EA node compares new cases against the entity data in the repository.
The SNA Group Analysis node builds a model of a social network based on input
data about th e social groupi ngs within the network. This technique iden t i es links
between the group members, and analyzes the interactions within t he groups to
produce key performance indicators (KPIs). The KPIs can be used for purposes such
as churn prediction , anomaly detection, or group leader identication.
The SNA Diffusion Analysis node models the ow of i nformation from a group
member to their social environment. A group member is assigned an initial weighting,
which is propagated across th e network as a gradually reducing gure. This process
continues until each member of the network has been assigned a weighting relative to
the original group member, according to the amount of information that has reached
them. The individual member scores are then derived directly from these weightings.
In this way, for example, a service provider could identify customers that are at a
higher risk of churn according to their relationship with a recent churner.