Search results

1 – 3 of 3
To view the access options for this content please click here
Article
Publication date: 12 May 2020

Shao-Ming Xie and Chun-Yao Huang

Predicting the inactivity and the repeat transaction frequency of a firm's customer base is critical for customer relationship management. The literature offers two main…

Abstract

Purpose

Predicting the inactivity and the repeat transaction frequency of a firm's customer base is critical for customer relationship management. The literature offers two main approaches to such predictions: stochastic modeling efforts represented by Pareto/NBD and machine learning represented by neural network analysis. As these two approaches have been developed and applied in parallel, this study systematically compares the two approaches in their prediction accuracy and defines the relatively appropriate implementation scenarios of each model.

Design/methodology/approach

By designing a rolling exploration scheme with moving calibration/holdout combinations of customer data, this research explores the two approaches' relative performance by first utilizing three real world datasets and then a wide range of simulated datasets.

Findings

The empirical result indicates that neither approach is dominant and identifies patterns of relative applicability between the two. Such patterns are consistent across the empirical and the simulated datasets.

Originality/value

This study contributes to the literature by bridging two previously parallel analytical approaches applicable to customer base predictions. No prior research has rendered a comprehensive comparison on the two approaches' relative performance in customer base predictions as this study has done. The patterns identified in the two approaches' relative prediction performance provide practitioners with a clear-cut menu upon selecting approaches for customer base predictions. The findings further urge marketing scientists to reevaluate prior modeling efforts during the past half century by assessing what can be replaced by black boxes such as NNA and what cannot.

Details

Asia Pacific Journal of Marketing and Logistics, vol. 33 no. 2
Type: Research Article
ISSN: 1355-5855

Keywords

To view the access options for this content please click here
Article
Publication date: 23 February 2010

I‐Ping Chiang, Chun‐Yao Huang and Chien‐Wen Huang

There has been considerable discussion of various aspects of the “Web 2.0” concept in the past several years. However, the Web 2.0 concept as a whole has not been analysed…

Abstract

Purpose

There has been considerable discussion of various aspects of the “Web 2.0” concept in the past several years. However, the Web 2.0 concept as a whole has not been analysed through the lens of the Web 1.0 metrics on which managers rely heavily for planning and evaluation. This paper aims to analyse the relationships among a site's audience metrics and its degree of Web 2.0‐ness.

Design/methodology/approach

Data collected from an online panel's clickstreams were aggregated to derive the web audience metrics. A web site's degree of Web 2.0‐ness was evaluated through a three‐step procedure by a series of binary criteria as to whether the site accommodates popular Web 2.0 applications. Pearson and Spearman correlations were conducted for the empirical analysis of data consisting of clickstreams gathered from an online panel coupled with expert scoring of web sites.

Findings

It was found that the size of a web site's visitor base is positively associated with the average number of page views per visitor. The average number of page views per visitor is in turn positively associated with the speed at which the visitors consume the site's content. Furthermore, a site's degree of Web 2.0‐ness is positively associated with the average number of page views per visitor and the speed of content consumption on the site.

Practical implications

First, the “double jeopardy” phenomenon of small brands found in the consumer package goods market is also observed for small sites in cyberspace in terms of audience metrics. Second, the accommodation of more Web 2.0 applications in a web site enhances the site's attractiveness so that its visitor base grows and its visitors will have a deeper relationship with the site.

Originality/value

This paper examines the Web 2.0 phenomenon through the Web 1.0 lens by exploring the relationships among web audience metrics and the degree of Web 2.0‐ness across web sites. It characterises the relationships among a web site's audience metrics and those between such metrics and the site's degree of Web 2.0‐ness. In addition this study fills an important gap in the literature and could serve as a stepping‐stone for further exploration of Web 2.0 issues from the market perspective.

Details

Online Information Review, vol. 34 no. 1
Type: Research Article
ISSN: 1468-4527

Keywords

To view the access options for this content please click here
Article
Publication date: 20 September 2013

Hua-Ning Chen and Chun-Yao Huang

– The current research aims to explore variables that explain the differences in online reviewers' behavior.

Abstract

Purpose

The current research aims to explore variables that explain the differences in online reviewers' behavior.

Design/methodology/approach

The authors' panel dataset is compiled from Amazon.com's book section and uses publicly available information about reviewers in combination with the reviews they wrote. The authors utilize the Pareto/NBD model with time-invariant covariates. The model's parameters are estimated using maximum likelihood estimates (MLE) with MATLAB software.

Findings

This study contributes to the literature by exploring how the characteristics of reviews and the reviewers might shape consumer review frequency and continuity. Specifically, the authors' results show that review ratings, comments on a review, and helpful votes have a positive association with review frequency and continuity. Furthermore, the length of the textual review has a positive relationship with review frequency, but a negative relationship with review continuity. Relative to anonymous reviewers, people who write reviews and use their real names post reviews less often, but their review continuity is longer.

Originality/value

This paper is the first to identify empirically variables that explain review frequency and continuity, thus enabling companies to gain a better understanding of their reviewer base and hence to manage online word-of-mouth more efficiently. It is the first study to apply a well-known behavioral model to address online review behavior.

Details

European Journal of Marketing, vol. 47 no. 10
Type: Research Article
ISSN: 0309-0566

Keywords

1 – 3 of 3