Online newspaper subscriptions - using machine learning to reduce and understand customer churn

Aug 3, 2026

Uploaded by Maeve

Modelling customer loyalty is central to customer relationship management in digital subscription news models. Subscription services require evidence-based retention strategies because churn threatens media sustainability. This study models the propensity to churn for online subscribers of a Portuguese newspaper using a machine learning approach. Two models are developed and evaluated across two timeframes, covering all B2C subscriptions and B2C nonrecurring subscriptions, revealing churner patterns that support targeted churn prevention and retention actions for marketing and editorial teams.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages25

Reading Time1 h 3 min

AccessFree to download

Abstract

Introduction

Revenue models and paywalls

Prior research and motivation

Journal of Media Business Studies ISSN: (Print) (Online) Journal [homepage: ](homepage: www.tandfonline.com/journals/romb20)[www.tandfonline.com/journals/romb20](homepage: www.tandfonline.com/journals/romb20) Online newspaper subscriptions: using machine learning to reduce and understand customer churn L úcia Madeira Belchior, Nuno António & Elizabeth Fernandes To cite this article: L úcia Madeira Belchior, Nuno António & Elizabeth Fernandes (22 Apr 2024): Online newspaper subscriptions: using machine learning to reduce and understand customer churn, Journal of Media Business Studies, DOI: 10. 1080/16522354 .2024.2343638 To link to this article: [https://doi.org/10.1080/16522354.2024.2343638](https://doi.org/10.1080/16522354.2024.2343638) © 2024 The Author(s) . Published by Informa UK Limited, trading as Taylor & Francis Group. | Published online: 22 Apr 2024. | | --- | | Submit your article to this journal | | Article views: 95 | | View related articles | | View Crossmark data | Full Terms & Conditions of access and use can be found at [https://www.tandfonline.com/action/journalInformation?journalCode=romb20](https://www.tandfonline.com/action/journalInformation?journalCode=romb20) JOURNAL OF MEDIA BUSINESS STUDIES [https://doi.org/10.1080/16522354.2024.2343638](https://doi.org/10.1080/16522354.2024.2343638) Online newspaper subscriptions: using machine learning to reduce and understand customer churn Lúcia Madeira Belchior a, Nuno António a and Elizabeth Fernandes b a NOVA Information Management School (NOVA IMS), Universidade NOVA de Lisboa, Lisbon, Portugal; bISCTE – Instituto Universitário de Lisboa (ISCTE-IUL), ISTAR, Avenida das Forças Armadas, Lisboa, Portugal ABSTRACT Modelling customer loyalty has been a central issue in customer relationship management, particularly in digital subscription business models. To guarantee news media sustainability, publishers implemented subscription models that need to define successful retention strategies. Thus, churn management has become pivotal in the media subscription business. The present study aims to understand what drives subscribers to churn by performing a Machine Learning approach to model the propensity to churn of online subscribers of a Portuguese newspaper. Two models were developed, tested, and evaluated in two timeframes. The first one considered all Business to Consumer (B2C) subscriptions, and the second only the B2C nonrecurring subscriptions. The experimental results revealed important patterns of churners, which allowed the marketing and editorial teams to implement churn prevention and retention measures. ARTICLE HISTORY Received 27 February 2023 Accepted 8 April 2024 KEYWORDS Churn prediction; online subscriptions; data mining; digital journalism; reader engagement Introduction News media traditionally base their business models on a combination of sales and advertising revenue (Fletcher & Nielsen, 2017) . The economic recovery from the 2008 crisis (Arrese, 2016) and the recent COVID-19 pandemic, coupled with a digital transformation and reader habits changes, induced publishers to re-evaluate their business models (Newman, Fletcher, Robertson, et al., 2022) . To diminish and offset the obstacles caused by the previously mentioned difficulties, newspaper companies are focusing on digital information business models (Cardoso et al., 2020) . Online newspapers’ primary sources of revenue are advertising and online subscriptions, mainly in the form ofpaywall models (Pattabhiramaiah et al., 2019). Nonetheless, the first does not create a long-lasting relationship with the users and can be avoided with the use of ad blockers (advertisement blockers). Hence, the latter has been adopted by many publishers to increase revenue through subscription business models (Newman et al., 2019) . CONTACT Nuno António [nantonio@novaims.unl.pt](nantonio@novaims.unl.pt) NOVA Information Management School (NOVA IMS), Univer

FAQs

What is the main goal of the study on online newspaper subscriptions?

To identify what drives subscribers to churn by using machine learning to model the propensity to churn for online subscribers of a Portuguese newspaper.

How many machine learning models are developed, and what do they cover?

Two models are developed and tested across two timeframes: one for all B2C subscriptions and another focused only on B2C nonrecurring subscriptions.

What practical value do the results provide to news organizations?

The results reveal important patterns of churners, enabling marketing and editorial teams to implement churn prevention and retention measures.

Aug 3, 2026

Uploaded by Maeve