| |
 |
 |
|
Last update: February 19, 2014
|
|
|
 |
 |
|
|
Bounded Trends Fitness Function
The Bounded Trends fitness function
is a multi-objective function that explores the idea of trends
and attributes rewards or punishments when a model hits or not on the trend.
It also combines the up/down hits with the
Root Relative Squared Error (RRSE).
The RRSE component is implemented so that you can choose different
simple models besides the usual target average.
Furthermore, it allows you to set boundaries for the model output,
which the learning algorithms will try to approach.
The Bounded Trends fitness function is particularly useful for time series data.
See Also:
Related Tutorials:
Related Videos:
|
|
|
|
|
