Repository logo
 

Personalized call center traffic prediction to enhance management solution with reference to call traffic jam mitigation - a case study on Telecom New Zealand Ltd.

Files

Dissertation(4.32 MB)

Date

2008

Authors

Supervisor

Pang, Paul

Item type

Thesis

Degree name

Master of Computer and Information Sciences

Journal Title

Journal ISSN

Volume Title

Publisher

Auckland University of Technology

Abstract

In today’s world call centers are operated as service centers and means of revenue generation. The key trade-off between customer service quality and efficiency of business operations faced by an operations manager in a call center is also the central tension that a human resource manager needs to manage (Aksin, Armony, & Mehrotra, 2007). By looking at the importance of providing efficiency at service quality, this dissertation conducts the research which describes forecasting approaches that can be applied to any call center. A case study research is conducted on Telecom New Zealand call center data which is based on a 15 minutes call interval data collected from call centers for the years 2007 and 2008 during the period of normal and abnormal (i.e. traffic jam) call distributions. Specifically, this research proposed a novel personalized call prediction method considering the importance of agent skill information for call center staff scheduling and management. Applying the proposed method, two call broker models: (1) personalized agent software broker, and (2) supervisor involved personalized software broker are further developed in this dissertation to construct a new generation call center IT solution for small size companies, and as well for large companies such as Telecom New Zealand. In this dissertation, a problem – solution approach is implemented. An initial step for problem generalization is to analyze and perform call predictions. The existing methods for call predictions implement inductive systems and are based on global models and thus cannot generate consistently good prediction accuracy, especially when traffic jam is confronted and/or if there is an abnormal increase of call volume which in turn makes calls to be abandoned affecting the service levels in the call center. In addition, since increase in the number of agents cannot be changed at short intervals of time, a personalized approach models an intelligent broker for every individual agent in the call center. This in turn expected to improve the generalworking efficiency of a call center, as compared to the traditional approach that use merely one broker for a number of agents. This concept is implemented using the proposed personalized prediction method, and demonstrated while comparing with other methods on call volume prediction experiments over real data streams from Telecom New Zealand. The proposed two broker models are both based on Personalized Prediction method. The first model uses the concept of software call broker which aims to implement the proposed prediction method as an Automatic Call Distributor (ACD). The second model, the supervised call broker is based on the concept of real time supervised observations of agent’s performance and then computing predicted calls for each agent. The broker implements the assisted knowledge of supervisor to select an appropriate agent to service the customer request. The proposed call broker models will depict as IT solutions for traffic jam problem. The Traffic Jam as addressed in the dissertation conducts the cost and return calculation as a measure for TNZ Return on Investment (ROI). While introducing the concept of traffic jam problem solving here from section 4.5.2, the non-personalized prediction method could release the traffic jam in 8.60 days with a saving in time of 1.40 days. This is in contrast to the personalized prediction method that releases the traffic jam in 8.48 days and a saving of 1.52 days. Meanwhile, the supervised call broker model can release a traffic jam in 8.04 days with a saving of 1.96 days to predict the traffic jam. The dissertation summarizes that, the intensity of traffic jam and cost/output analysis for scheduling more agents to improve the service factors at short intervals of time will be a challenging task for any call center. As observed the benefits of savings is achieved by improvements in the level of service that couldn’t outweigh the costs of hiring new agents and in addition, couldn’t improve the profitability of Telecom New Zealand during the period of traffic jam. Hence, the proposed method of personalized broker with supervisor role can be an alternative to provide a better service levels to any bigger call centers like Telecom New Zealand. For any other small size call centers consisting of 2-5 agents, implementing software call broker will resolve the problem of traffic jam and as a best possible solution to maximize Return on Investment.

Description

Keywords

Call centre, Fuzzy inference, Experimental approach, Contact centre, Management, Call volume prediction

Source

DOI

Publisher's version

Rights statement

Permanent link

https://hdl.handle.net/10292/479

Collections

Masters Dissertations