Discovering customer segments through interaction behaviors for home appliance business

Abstract Market segmentation has become a crucial step in developing a successful marketing strategy, as it allows businesses to understand their target audience on a deeper level and create personalized experiences for different customer groups. For customer cluster analysis, this study expanded th...

Full description

Saved in:
Bibliographic Details
Main Author: Youngjung Suh
Format: Article
Language:English
Published: SpringerOpen 2025-03-01
Series:Journal of Big Data
Subjects:
Online Access:https://doi.org/10.1186/s40537-025-01111-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850072377826738176
author Youngjung Suh
author_facet Youngjung Suh
author_sort Youngjung Suh
collection DOAJ
description Abstract Market segmentation has become a crucial step in developing a successful marketing strategy, as it allows businesses to understand their target audience on a deeper level and create personalized experiences for different customer groups. For customer cluster analysis, this study expanded the customer base of existing research from market segmentation studies based on customer demographics and purchasing behavior to include pre-purchase perception/exploration as well as post-purchase actual usage data. To this end, all interactions with customers were designed based on CEJ (Customer Experience Journey), and then interaction characteristic variables were created. Here, we applied two data mining algorithms, clustering and NMF (Non-negative Matrix Factorization), based on the data of 40,911 actual customers in the home appliance business using the designed multidimensional behavioral characteristic variables. We conducted an evaluation study on the validity of cluster analysis by evaluating both the accuracy and stability (consistency) of the resulting customer segments from the two methods. Through analyzing the key characteristic data of the resulting customer segments, we investigated the technical advantages of each method and overlap/deviation of the resulting segments to provide analysis results. Thus, companies can focus their resources and efforts on the most profitable and receptive consumer groups by identifying the customers into distinct segments, as well as discover new business opportunities by figuring out less common but peculiar customer behaviors.
format Article
id doaj-art-91c0c6db5a9147bc8a8bad8d242845c8
institution DOAJ
issn 2196-1115
language English
publishDate 2025-03-01
publisher SpringerOpen
record_format Article
series Journal of Big Data
spelling doaj-art-91c0c6db5a9147bc8a8bad8d242845c82025-08-20T02:47:06ZengSpringerOpenJournal of Big Data2196-11152025-03-0112113910.1186/s40537-025-01111-yDiscovering customer segments through interaction behaviors for home appliance businessYoungjung Suh0Department of Computer Science and Engineering, Kongju National UniversityAbstract Market segmentation has become a crucial step in developing a successful marketing strategy, as it allows businesses to understand their target audience on a deeper level and create personalized experiences for different customer groups. For customer cluster analysis, this study expanded the customer base of existing research from market segmentation studies based on customer demographics and purchasing behavior to include pre-purchase perception/exploration as well as post-purchase actual usage data. To this end, all interactions with customers were designed based on CEJ (Customer Experience Journey), and then interaction characteristic variables were created. Here, we applied two data mining algorithms, clustering and NMF (Non-negative Matrix Factorization), based on the data of 40,911 actual customers in the home appliance business using the designed multidimensional behavioral characteristic variables. We conducted an evaluation study on the validity of cluster analysis by evaluating both the accuracy and stability (consistency) of the resulting customer segments from the two methods. Through analyzing the key characteristic data of the resulting customer segments, we investigated the technical advantages of each method and overlap/deviation of the resulting segments to provide analysis results. Thus, companies can focus their resources and efforts on the most profitable and receptive consumer groups by identifying the customers into distinct segments, as well as discover new business opportunities by figuring out less common but peculiar customer behaviors.https://doi.org/10.1186/s40537-025-01111-yBig data applicationsMarket segmentationMachine learningCluster analysisFeature selectionCustomer retention management
spellingShingle Youngjung Suh
Discovering customer segments through interaction behaviors for home appliance business
Journal of Big Data
Big data applications
Market segmentation
Machine learning
Cluster analysis
Feature selection
Customer retention management
title Discovering customer segments through interaction behaviors for home appliance business
title_full Discovering customer segments through interaction behaviors for home appliance business
title_fullStr Discovering customer segments through interaction behaviors for home appliance business
title_full_unstemmed Discovering customer segments through interaction behaviors for home appliance business
title_short Discovering customer segments through interaction behaviors for home appliance business
title_sort discovering customer segments through interaction behaviors for home appliance business
topic Big data applications
Market segmentation
Machine learning
Cluster analysis
Feature selection
Customer retention management
url https://doi.org/10.1186/s40537-025-01111-y
work_keys_str_mv AT youngjungsuh discoveringcustomersegmentsthroughinteractionbehaviorsforhomeappliancebusiness