Capturing the real customer experience based on the parameters in the call detail records /
It is not a surprise that in recent fierce market of telecommunication, CEM (Customer Experience-Management) has emerged as key differentiator. A positive customer experience leads to increased loyalty, lower churn rate, more recommendations and optimistic word of mouth. Researchers have defined the...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Kuala Lumpur :
Kulliyyah of Information and Communication Technology, International Islamic University Malaysia,
2019
|
| Subjects: | |
| Online Access: | http://studentrepo.iium.edu.my/handle/123456789/9701 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | It is not a surprise that in recent fierce market of telecommunication, CEM (Customer Experience-Management) has emerged as key differentiator. A positive customer experience leads to increased loyalty, lower churn rate, more recommendations and optimistic word of mouth. Researchers have defined the customer experience management as “the scale to meet or exceed customer expectations thus increases customer satisfaction, loyalty and advocacy”. A superior customer experience management is one of the sustainable competitive differentiator. In this era of technology, digital data became an asset of any business. Numbers of analytical techniques are used to extract meaningful information from collected data. Hence, face-to-face and voice interactions with customers are being steadily replaced by digital channels. This research proposes a technique that calculates the CEMI (Customer Experience Management Index) of subscribers of cellular network services providers by using their Call Detail Records (CDRs). Proposed technique can be applied on offline/historical and online CDRs. In the first phase of this research, CDR Dataset was collected, identified different communities by using classical algorithm of modularity. This study graded those communities based on revenue and then selected a most valued community based on ARPU (Average Revenue per User) of 200 subscribers or nodes. All subscribers are using the same cellular network operators residing in Islamabad, the federal capital of Pakistan. All these 200 subscribers were connected to different BS (Base Stations) and one common MSC (Mobile Switching Centre). In the second phase, a close-ended telephonic survey was prepared and conducted on 200 subscribers of targeted valued community or social network. Six attributes of telecommunication service are selected as part of survey i.e. network coverage, voice call quality, drop call rate, Short Message Service (SMS) delivery, internet service and call setup duration. The subscribers were asked to grade each attribute as per their experience while using that service and rate the service collectively in order to identify the overall experience. Genetic algorithm was applied to optimize the weights for each attribute to eventually formulate a mathematical model for Customer Experience Management Index (CEMI) calculation. The cost function used here is to minimize the error between weighted attributes based calculated CEMI and actual CEMI provided during survey process. By the end of second phase, the genetic algorithm has been trained to find out optimized weights and the most critical attributes that have direct impact on customer experience management. Same attributes are selected from CDRs, they are graded on the same scale that is used in survey based on the events, and flags present in the CDRs. While concluding the results, the obtained optimized weights are applied to the technical attributes of the CDRs data set and CEMI is calculated. In this study, a strong correlation between both the CEMIs is been discovered, thus approving its hypothesis that digital means can be applied to calculate customer experience on all valued customers and communities. This research is very significant in eliminating the use of conventional surveys for estimation of customer experience on a small sample set; the proposed technique calculates the CEMI in real-time thus enabling the service provider to take corrective measures in timely fashion. |
|---|---|
| Item Description: | Abstracts in English and Arabic. |
| Physical Description: | xiii, 119 leaves : colour illustrations ; 30cm. |
| Bibliography: | Includes bibliographical references (leaves 107-113). |