Enhancing the caller-agent relationship for skill-based routing in call centres | |
| Author | Sarkar, Siddharth Arnab |
| Call Number | AIT RSPR no.IM-07-05 |
| Subject(s) | Call centers Data mining |
| Note | A research study submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Information Management, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Research studies project report ; no. IM-07-05 |
| Abstract | In this world of information overload, the best practice to gain information to a level of knowledge is to extract what is required and eliminate what is not. This idea can be applied to any domain where "association" takes place. Association has a vast range, ranging from the one between sub-atomic particles, to one between human and material and human-human relationship is no exception. This association model can be used to identify "like" unseen associations. When an online shop can recommend its user what to buy, when a TV can recommend what to watch, why cannot a call centre recommend its user (caller), with whom (call centre agent) to speak to? After all it lies within the domain of "association". It is clearly visible in the call centre domain, that the agent's skills are rated by the manager's perception rather than the caller's; this is contrary to the customer centric philosophy of a call centre and is the root cause of all the dysfunctions. For e.g. a caller calls the call centre, and the call lands on an inefficient agent's desk (Why? because manager assigns agent to this type of service), after talking for ten minutes the issue is not resolved and he is transferred to another department where he faces the same situation, and he decides to abandon the call centre, at extreme the enterprise. And there should be a way not to be a victim of this situation. In this research, we reference to the World Wide Web, which uses collaborative filtering techniques to provide recommendation to its users. Applying the same technique in the call centre domain, required historical data is extracted from the real-time telephony database and filtered to create an implicit profile which contains the details of each and every interaction between a caller and an agent. The profile is based on previous interactions and used to recommend the present caller. A new caller cannot be recommended; instead his call is routed within the service level boundaries of skill-based routing, but the interactions are recorded in order to provide future recommendations. Thus, this system is a top-over on an existing skill-based routing, in other words, personalised skill-based routing. |
| Year | 2007 |
| Corresponding Series Added Entry | Asian Institute of Technology. Research studies project report ; no. IM-07-05 |
| Type | Research Study Project Report (RSPR) |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Information Management (IM) |
| Chairperson(s) | Vatcharapom Esichaikul; |
| Examination Committee(s) | Donyaprueth Krairit ;Janecek, Paul; |
| Scholarship Donor(s) | Asian Institute of Technology Fellowship; |
| Degree | Research Studies Project Report (M.Eng.) - Asian Institute of Technology, 2007 |