A Machine Learning Based Classification Method for Customer Experience Survey Analysis

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.

Application Programming Interface for a Customer Experience Analysis Tool

“…The novelty of the overall CX system could be established on the utilization of advanced ML algorithms to tackle the major obstacles in the evaluation of the CX metrics: 1) the lack of sufficient data and 2) the fact that the CX metric scores depend not only on the CX attributes, but also on other unidentified attributes, such as perception or emotional related attributes. As shown in previous studies [2] the use of the ML module significantly improved most of the examined statistical metrics. Further investigation will be performed in the following steps of the CX system development to test the ability of the proposed methods to capture the relation between the CX attributes and the NPS indicator.…”

“…The cornerstones of a CX based strategy are the CX metrics, such as the Net Promoter Score (NPS) which expresses the customer's likelihood to recommend the company's product and/or services [1]. Based on an extended data set from the telecommunication sector, several state-of-the-art Machine Learning (ML) where employed in order to clarify the relation between the NPS and the most significant CX attributes [2], [3]. The ML techniques, along with several graphical representation features were incorporated in an integrated application dedicated to the analysis of the NPS index.…”

Clustering Pengunjung Mall Menggunakan Metode K-Means dan Particle Swarm Optimization

“…Untuk mencapai tugas ini, pembelajaran mesin sudah diterapkan oleh banyak toko dan pasar lainnya [9]. mal atau pusat perbelanjaan memanfaatkan data yang mereka dapatkan saat bertransaksi dengan pelanggannya dan memanfaatkannya dengan mengembangkan model ML untuk menyasar yang tepat [10]. Hal ini tidak hanya meningkatkan penjualan & jumlah pengunjung yang datang tetapi juga meningkatkan efisiensi dalam berbisnis.…”

Multiclass Confusion Matrix Reduction Method and Its Application on Net Promoter Score Classification Problem

“…, K) is the satisfaction score of the same survey responder i, for CX attribute j and f is the function that allows for the association between these metrics. The problem of CX metric classification can be addressed based on machine learning algorithms as shown in [12]. The confusion matrix of this problem is a multiclass confusion matrix with a dimension equal to the number of different class labels (i.e., the CX metric score labels).…”

“…In this paper, the following algorithms have been tested for the NPS classification problem [12]: logistics regression (LR), k-nearest neighbor (k-NN), naïve Bayes (NB), support vector machines (SVM), decision trees (DT), random forest (RF), convolutional neural networks (CNN), and artificial neural networks (ANN).…”