DSC Tech Library
This section of our technical library presents information and documentation relating to Call Center technology and Best Practices plus software and products.
DSC is a leading provider of contact center technology and software solutions as well as predictive dialer phone systems for the modern call center. Customer contact center software includes CRM software and computer telephony integration solutions. These modern products help call center phone agents communicate effectively with your customers and prospects.
The following article presents product or service information relating to call centers and customer service help desks.
Call Center Simulation Modeling:
By Vijay Mehrotra, Department of Decision Sciences
Methods, Challenges, And Opportunities
College of Business - San Francisco State University
Jason Fama, Engineering Group, Blue Pumpkin Software Inc.
The call center itself features two queues: an Inbound
queue and an Outbound queue. The time period that we
are using for the analysis is one week.
The two agent groups and the basic routing logic are
illustrated in Figure 3. Calls from the Inbound queue will
arrive and be served by an agent from Group #1, the Inbound-
Only group. If no agent from this group is available,
the calls will wait in queue. If, after some predefined
period of time, the Inbound call has not yet been
served, it will then also queue for an agent from Group #2,
the Cross-Trained Outbound group.
Meanwhile, Group #2 and Group #3 agents will be
logged into a Predictive Dialer, which places Outbound
calls to prospects from a list. When an answer is detected
by the Predictive Dialer, the call is automatically routed to
one of the Outbound Specialists or one of the available
Cross-Trained Outbound agents. The agent then engages
in a collections discussion (if they have reached the Right
Party) or leave a message (if they have reached an answering
machine or another party on the same phone number).
Along with mailings to delinquent customers, these messages
will generate some calls to the Inbound queue.
4.3 Key Inputs: Call Forecasts
Call forecasts are typically driven by a combination of historical
data, time series model, and expert judgment. There
are two major types of call forecasts: call volumes and
Average Handling Time. Both are required for any basic
call center simulation.
Due to the telecommunication and call center industries’
history of using steady state M/M/n queue formulas
to derive the number of agents needed for each time interval,
it has been customary to translate call volume forecasts
into ? values for Poisson arrivals and AHT forecasts into µ
values for Exponential service times.
A great deal of research has been conducted on call
volume forecasting models, and the interested reader is referred
to Mabert (1985) and Andrews and Cunningham
(1995) for valuable discussions on this topic.
Forecasts must be created for each queue for each time
interval in the simulation period.
The most common call center forecasting approach is
to create weighted averages of historical data for specific
time intervals over the course of a week. For example, the
initial call volume forecast for 8:15 a.m. - 8:30 a.m. next
Tuesday might be computed as the average of call volume
for the 8:15 a.m. - 8:30 a.m. period on the past several
Tuesdays. From here, alterations may be (or more commonly,
should be!) made based on additional information
(e.g. specific marketing activities for a sales center or
emerging product issues for a technical support center) that
may cause volume to differ substantially from previous
4.3.1 Average Handle Time Forecasts
As mentioned earlier, most call center models assume that
call handling times are exponentially distributed. We
would recommend using more accurate distributional information
about call handling times whenever possible.
For example, it is common to find technical support call
center for which call handling times are bi-modal (easy
cases with a shorter mean, harder cases with a longer one).
However, the primary reason that the call center industry
accepts the assumption of exponential handling times is
because the ACD and CTI devices (the primary source for
historical call volume data) store only average handling
times at the interval level. With a dearth of consistent second
moment information available, we have thus accepted
this assumption far more often than we would like; in particular,
we have modeled exponential handling times in the
numerical example presented in Section 5.
Note: in this paper, we refer to Average Handling
Time, or AHT. However, when obtaining data from ACD
reports, it is not uncommon to find two fields that are then
summed together to compute AHT: Average Talk Time
(“ATT”) and After Call Work (“ACW”).
4.4 Key Inputs: Agent Schedules
Agent schedules can be thought of as a series of activities
taking place over the course of a day. For example, an
agent who comes to work at 8:00 am for a nine-hour shift
may have a 15-minute break at 9:45 am, lunch at 11:30 am,
an on-line training course from 1:00 – 2:00 pm, and a
break at 3:15 pm before leaving work at 5:00 pm.