skip to primary navigationskip to content

Cambridge Service Alliance

developing new understanding and approaches to complex service systems

Studying at Cambridge

 

Customer Experience Management Using Data Analytics

This study addresses the research question 'How can qualitative and quantitative measures be combined to measure the customer experience'.

Customer experience management is listed in the top ten priorities of CEOs around the globe. Carefully managing the customer experience can reap rewards including increased customer satisfaction and loyalty, increased revenue and greater employee satisfaction. Conceptualized as holistic, comprised of multiple touch points in an end-to-end journey the customer experience involves the customer’s cognitive, affective, emotional social and sensory elements. This conceptualization views the customer experience as a process rather than an outcome - a process made up of interactions and activities across multiple touch points with several employees, as well as other customers.

While it is acknowledged that the customer experience is complex and longitudinal, measurement is usually made at one point in time, typically at the end of the journey.  Such a “snap shot” approach does not adequately account for the multiple touch points.  Single measures taken at the end of the customer experience journey mask the underlying issues of concern, which are the basis for identifying improvements. Moreover, these individual single measures typically force customers to provide an “overall” assessment of the journey.  Not surprisingly, these aggregate single measures tend to mask the customer’s true feelings and evaluations of their experience. Even if multiple measures are taken at several touch points across the customer experience journey, they are often “averaged out”, masking important details that matter.

Research Objective:

This project seeks to create a novel way of analysing customer experience data, by combining qualitative and quantitative customer data that captures details of positive and negative experiences. Using a longitudinal customer data set of customer satisfaction data, that covering multiple key touch points for two case studies across a selection of service alliance partners, we will demonstrate a novel methodology for combining qualitative and quantitative customer data that captures details of positive and negative experiences to generate deep insights.

Research Question:

This study addresses the research question “How can qualitative and quantitative measures be combined to measure the customer experience”.

Approach:

customer experience diagramThe project will use text analytics approach to automate the process of analysing customer satisfaction data. In general, we used the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology for a linguistics-based approach using domain specificity. The text mining process adopted the following process: business and data understanding, training or model development and testing or model evaluation.

Outputs:

The outcome of 2015 research is a development and testing of customer experience text analytics method. The model will highlight the key priorities areas for customer experience improvement in B2B context. Specifically, the result of Text Analytics model will be:

  1. an identification of  the most important resources and activities for the customer when using a service.
  2. an evaluation of customer compliments and complaints. This will result to direct actions for improving the customer service experience. 

Contact Details: Dr Mohamed Zaki 

RSS Feed Latest news

Webinar - Customer Loyalty Predictive Model

Jan 10, 2017

9 January 2017 - The Fallacy of the Net Promoter Score: Customer Loyalty Predictive Model - Mohamed Zaki

Webinar - Feedback from the Frontline

Dec 13, 2016

12 December 2016 - Feedback from the Frontline: Engaging front-line employees in service innovation - Florian Urmetzer

Ecosystems Value Framework Paper

Dec 12, 2016

The December Paper on 'The Ecosystem Value Framework: Supporting Managers to Understand Value Exchange between Core Businesses in Service Ecosystems', by Florian Urmetzer, Veronica Martinez and Andy Neely.

December 2016 Newsletter

Dec 01, 2016

December 2016 Alliance Newsletter

Classification of Noisy Data

Nov 28, 2016

November paper on 'Classification of Noisy Data: An Approach Based on Genetic Algorithms and Voronoi Tessellation' by Abdul Rauf Khan, Henrik Schiøler, Torben Knudsen, Murat Kulahci and Mohamed Zaki

View all news

Upcoming events

Shift to Services Executive Education Programme

Apr 04, 2017

IfM, Cambridge, UK

Cambridge Service Week 2017 - Academic Conference

Oct 05, 2017

IfM, Cambridge, UK

Upcoming events