A Machine Learning Based Classification Method for Customer Experience Survey Analysis

Ioannis Markoulidakis,George Kopsiaftis,Ioannis Rallis,Ioannis Georgoulas,Nikolaos Doulamis,Anastasios Doulamis

doi:10.3390/technologies8040076

Ioannis Markoulidakis, George Kopsiaftis + Show 4 more

Open Access

https://doi.org/10.3390/technologies8040076

Copy DOI

Journal: Technologies	Publication Date: Dec 7, 2020
Citations: 6	License type: CC BY 4.0

Affiliation: National Technical University of Athens

Abstract

Customer Experience (CX) is monitored through market research surveys, based on metrics like the Net Promoter Score (NPS) and the customer satisfaction for certain experience attributes (e.g., call center, website, billing, service quality, tariff plan). The objective of companies is to maximize NPS through the improvement of the most important CX attributes. However, statistical analysis suggests that there is a lack of clear and accurate association between NPS and the CX attributes’ scores. In this paper, we address the aforementioned deficiency using a novel classification approach, which was developed based on logistic regression and tested with several state-of-the-art machine learning (ML) algorithms. The proposed method was applied on an extended data set from the telecommunication sector and the results were quite promising, showing a significant improvement in most statistical metrics.

Highlights

Customer Experience (CX), since its introduction as a concept [1,2,3,4], has evolved as a key differentiation strategy element across industries, especially in mature markets with low product differentiation opportunities
The new classification allows for the employment of the same Net Promoter Score (NPS) scoring process and seems to have an improved performance in terms of accuracy and F1-score, compared to the original NPS analysis
The paper provides an example of how the proposed method can support the prioritization of CX actions based on logistic regression and a set of monthly NPS survey data

Summary

Introduction

Customer Experience (CX), since its introduction as a concept [1,2,3,4], has evolved as a key differentiation strategy element across industries, especially in mature markets with low product differentiation opportunities. As more and more companies are adopting CX excellence strategies, customers receive a higher quality of experience, which further raises the bar of CX competition. In such a competitive environment, CX analytics is a topic that attracts the attention of the industry, especially focusing on methods that lead to actionable insights. The cornerstone of a CX strategy implementation program is the metric used to measure the performance of both the company and its market competitors. The Net Promoter Score (NPS) [5]

Results

Discussion

Conclusion