| MiningSolve
Benefits |
| |
| |
- Generates
Models 100 to 1000 Times Faster
than non-automated mining.
|
- Produces
Higher Performing Models: By
rapid testing of models through varying algorithms, sub-algorithms,
transforms, iterations, and criteria.
|
- Leverages
the Most Comprehensive Set of Time-Honored Algorithms Worldwide:
We leverage the entire back-end of the SPSS kernel through OLE
automation.
|
- Encapsulates
Complexity: A built-in model
creation wizard guides the user to answer simple questions to
set up the models. A rule database interprets the answers and
creates the syntax to create and track the performance of the
models.
|
- Validates
Using Hold-Back Sampling: The
only truly valid way to test model performance is to apply it
to "hold-back" respondents, respondents who were not
used in developing the model, but for whom we already know their
"disposition" (i.e., hold-back sample validation).
|
- Adapts
In Real Time Based on Successes:
If higher performing models are produced by certain algorithms
over others, MiningSolve redeploys effort in real time to
produce more of those higher performing models. Technology: Automated
Adaptive Resourcing (AAR).
|
- Learns
from Previous Successes, storing
them in a Rules Repository.
|
- Recommends
Best Models based on the comparing lifts at different campaign
depths.
|
- Distributed:
Installable on a single CPU, or on PC's on your LAN, WAN or over
the Internet.
|