| --> |
At CallCenterOps.com we’re dedicated to providing information about operations management to those involved in real-time customer service via call centers.
Learn how to advertise on this site. |
|
|||||||
| General Discussion The CallCenterOps Forum allows you to seek the advice of other knowledgeable call center professionals. Post your call center related question and contribute your opinion to others seeking advice. (No advertising is accepted - posts will be removed.) |
![]() |
|
|
LinkBack | Thread Tools | Display Modes |
|
|||
|
Answering Machine detection
Hello,
This is regarding detection rate for answering machines. I have a software only dialer. The tone detection and call progression is done by Dialogic boards. The reports that are generated show the detection of answering machine to be about 60%, which I believe is incorrect. Is this is fault of the Dialogic boards? Do dialers that come with their own hardware (Davox/Mosiax) improve performace? (As compared to Dialogic?) What would be the accuracy of Answering m/c detection for Davox and Mosaix? Is there any other way out of this, like passing all calls to Agents without automatic detection? Thanks for helping out.
__________________
Maulik Shah, Avon Technologies (India) Pvt. Ltd. |
|
|||
|
ANS Detection
Mlik,
From my experience with Davox, EIS and Melita I have found a difference in % detected. For a "consumer" call the answering detection should be in the 94% range. Davox and EIS have this percentage. Answering detect is based on waiting for a pause after the initial sentence ie " Hello, we are not home right now. Please leave a message at the beep. PAUSE" Dialer software comes into play here. Calling a "business" is different because a long intro occurs and each business may have a vastly different message. For business calling you may consider turning detect off because the % is low and may cause more trouble than it is worth. SBB2002 |
|
|||
|
Thanks SBB,
Is there another way to detect an answering machine other than listening to the pause. Does the machine not have any specific signals that the telephony cards may detect. As you said, in case of businesses, efficiency may suffer
__________________
Maulik Shah, Avon Technologies (India) Pvt. Ltd. |
|
|||
|
Answering Machine Detection
Dialogic uses what is known as perfect call to determmine weather an answer was a human or a machine. this system was desgned a while ago and has not been updated. this can present problems detecting a human when they.... use a cell phone... use a cordless phone..... or in general have a bead signal. However you should see fairly accurate results. to determin if the results are corect or not i would wnat to know how many calls were dialed and what were the other results. The perfect call can be "tweaked " for better perfomance but it would have to be done programamtically in the source code of the dialer. we develeop with the dialogic API's directly and do just that. I dont know if you would have that kind of capability with your system. check out our website ... if you have any questions give us a call.
thanks Brian Lorenz Mediatel Data USA |
![]() |
| Thread Tools | |
| Display Modes | |
|
|