Forecasting Unknown Data

[sjkleit]

My company is about to engage in a system wide conversion that will affect an application that most of our customers use. We have no historical data for a conversion on this scale. Has anyone out there experienced the same kind of circumstance, and if you have, what did you base your forecast for call volume, average call handling time and average call hold time on? Thank you in advance for any suggestions that you might offer.

[n_meghanath]

Since you don't have anything to based on, you may want to take the following assumptions

Probable Users of the applications (on a day).
Probable % of customer who will call the helpline.
Peak time (Applications uses)

This may allow you to come up with a figure

Further based on the forecast of day 1 (post application conversion) and the available agents to handle the forecasted volume you may be able to project the repeat calls owing to unanswered calls.

I am not too sure if this would give you a good forecast but I also know that you don't have any alternative unless you have some figures to rely on to work on the forecast.


Meghanath

[sjkleit]

This is along the lines of what we are trying but your input gives me a bit more dimension. Thanks!

[n_meghanath]

It would be great if you could share how effective is the approach.

Meghanath