Lucent Technologies CentreVu Release 3 Version 5 Forecast User Manual page 19

Introduction
Getting Started with Forecasts
Expected Calls
Seasonal Trending
CentreVu CMS R3V5 Forecast 585-215-825
You enter the number of calls you expect for
the forecasted day. CentreVu CMS checks the
data points to find the percentage of historical
calls that arrived in each intrahour interval.
CentreVu CMS then distributes your expected
calls among the forecast day's intervals using
those same percentages.
CentreVu CMS finds the average number of
calls per interval in the current data points.
Based on an earlier seasonal trend base date
(a seasonal trend base date is a date in the
past that you think is similar to the current day),
CentreVu CMS also finds the average number
of calls per day in a parallel set of data points
(these averages use the data weights).
CentreVu CMS then scales up or down the
average found in the current data points
according to the ratio of the seasonal trend
base date to the seasonal average. Thus, with
seasonal trending, CentreVu CMS uses data
for a seasonal set of data points to determine
the data in the current set of data points.
Look at the example in
points for today, May 28, are 1 week apart,
when you select a seasonal trend base date of
1 year (52 weeks) ago, CentreVu CMS
automatically uses data points for last year
from the base date that are also 1 week apart.
Figure 1-3. Since data
1-7