Mittuniversitetet

In emergency call centers (for police, firemen, ambulances) a single event can sometimes trigger many incoming calls in a short period of time. Several people may call to report the same fire or the same accident, for example. Such a sudden burst of incoming traffic can have a significant impact on the responsiveness of the call center for other events in the same period of time. We examine data from the SOS Alarm center in Sweden. We also build a stochastic model for the bursts. We show how to estimate the model parameters for each burst by maximum likelihood, how to model the multivariate distribution of those parameters using copulas, and how to simulate the burst process from this model. In our model, certain events trigger an arrival process of calls with a random time-varying rate over a finite period of time of random length.

A key task of managing an inbound call center is in estimating its performance and consequently plan its capacity, which can be considered a complex task since several system variables are stochastic. These issues are highly crucial for certain time-sensitive services, such as emergency call services. Waiting times affect the service quality of call centers in general, but various customers may place different waiting time expectancies depending on the need. Call center managers struggle to find the relationship between these expectations to their strategical, tactical and operational issues. They are assisted by queueing models that approximate the outcome. Simple setups use analytical approximations while a network of multi-skilled agents serving several customer classes is dependent on computer simulations. Regardless of simple or complex setups, models assume that the system components are homogenous, that the components have some parametric distribution, and that they remain the same regardless of the setup. Human resource and marketing research show that such status quo assumptions are not highly reliable. As an example, customer experience is often affected by the skill of the agent, and agents themselves are affected by their workload and duties, which inter alia affect their efficiency. This thesis aim to assist the Swedish emergency call center with a strategical issue, which require detection of some causalities in the set of system components. The overall aim is to design a simulation model, but such model requires a lot of detailed system knowledge, which itself adds to the knowledge gap in the research field. Findings that contribute to the scientific knowledge body include the burst model that addresses some of the non-stationarity of call arrivals, since some rapid rate increments derives from a latent emergency event. Other contributions are the introduction of stochastic agent behavior, which increases the uncertainty in queueing models; and the service time relationship to geographical distance. The latter may involve general evidence on how area-specific understanding and cultural differences affect the quality of service. This is important for organizations that consider off-shoring or outsourcing their call center service. These findings, along with several undiscovered and unknown influencers, are needed in order to design a reliable simulation model. However, the proposed model in this study cannot be rejected, in terms of waiting time replication. This robust model allowed traffic routing strategies to be evaluated and also assisted managers of the emergency call center into a strategical shift in the late 2015.

Bin packing problem has gained a wide interest in academia and in practice since the problems quickly becomes intractable as the problem grows. In this paper two models are compared: one model that generates exact solutions for bin packing problem and one that uses the same fundamental approach on the problem but extended with a heuristic combination of next-fit and a combinational best-fit. The results proves that the heuristic approach has competitive features of linearity as the problem grows, but still with satisfying optimums in the evaluated instances.

Distancing contact centers from the customer is a highlighted strategic measure in call center industry, argued to reach higher efficiency and reduce operational costs. There is however a lack of empirical evidence about the side-effects of distancing, and academia has requested a mapping of the hidden costs accompanied with moving the operator from its customer. This study examines the relationship between service time and distance, by a designed quasi-distance scale between the customer and the operator. The result indicates a distance dependency, but the main effect is not due to the distance but rather due to characteristics of the office and caller origin independently. The study also stipulate a framework how big data can be converted into valuable information to call center managers, and provide insights of areas where further training and technological improvements should be focused.

The Swedish emergency call center fail in achieving government agreement regarding availability. In this project we evaluate different traffic management strategies using our designed discrete event simulation model, also supposed to apply as a traffic planning tool assisting daily issues. Outputs from the study has so far contributed to the managerial decision of implementing a new strategy, currently being evaluated. The result from this evaluation is statistical significant. As a result of our evaluation we have pinpointed some challenges of great value for the management team. For instance, if they measure sociological parameters, the model performance will be significantly improved.

The Swedish emergency call center (SOS Alarm) has recently struggled in fulfilling the stakeholder requirements regarding service levels. One of the effects in their improvement efforts is this funded PhD project with the overall aim to provide better knowledge regarding the queueing system and the effects of implementing different queuing strategies. The idea is to achieve better resource efficiency and a more even distributed workload on the operators and the objective of this study is to analyze the effects of implementing a routing setting where calls is routed between different catchment areas if not answered within a threshold value. The method is discrete event simulation due the complexity of introducing multi-classes and routing in analytical approaches. Simulation allows detailed modeling and experimental tests of system configurations without exposing citizens to unnecessary risks. So far the results from the simulation has shown to better replicate the real-life situation and is therefore superior to the analytical approaches, such as the widely used Erlang-C, in predicting system performance. The project has so far stipulated statistical evidential guidelines of different routing strategies. The designed simulation model has been validated and will be further evaluated and tested in the daily operations at SOS Alarm.

In telecommunication research, the assessment of strategic and operational performance has gained a lot of interest. So far, the variability within the operational research of telecommunication derives from the stochastic nature of call arrivals, call duration and abandonments. This study extends the stochastic drivers to capacity by incorporating agent behavior. In this study, we model a Discrete-Event-Simulation model of the Swedish emergency call service provider to assist the strategic issue of skills-based routing. Because of the pull system, we designed skills-based routing using an event-dependent overflow setting with a fixed waiting time threshold, where calls become visible to extended agent classes after a threshold value, providing an advantage to primary idle agents to answer before idle secondary agents. Our model mimics the tail of waiting times better than conventional methods. Because of the accompanied calculation opportunities, the model has assisted both strategic and operational issues in the organization. In addition to practical implications, the study proves that the stochastic nature of agent behavior is crucial. From a queueing theory perspective, the study provides interesting routing effects for an event-dependent overflow setting using a fixed waiting time threshold in a combined “X-N-design”, previously unexplored in research.