University of Twente Student Theses
Discovering customer clusters using unsupervised machine learning to aid the marketing strategy: a case study with an online retail webshop SME.
Reuvers, S. (2021) Discovering customer clusters using unsupervised machine learning to aid the marketing strategy: a case study with an online retail webshop SME.
|
PDF
1MB |
| Abstract: | The rise of digital technologies has given businesses access to large amounts of data. However, the ability of (small) businesses to gain valuable marketing insights from this data is limited. The first aim of this study is to identify customer clusters using a clustering approach and algorithm in data collected during online customer-business interactions. To do this, a literature review and a case study are conducted, using the Knowledge Discovery in Databases process as a research methodology. The results of the literature review show that partitioning-based clustering, using k-prototype, is a suitable approach in analyzing a mixed and large dataset. The results of the first cluster analysis, based on individual customer data, show that two customer clusters have been found. The results of the second cluster analysis, based on grouped visitors data, show that two visitor clusters have been found. The second aim of this study is to develop a marketing strategy for the discovered clusters. The marketing strategies for the discovered clusters include providing personalized products, offerings, and content using e-mail marketing campaigns, loyalty programs, and recommender engines. This research also argues that optimization strategies (SEO, SEA) can be developed based on the discovered clusters. |
| Item Type: | Essay (Master) |
| Faculty: | BMS: Behavioural, Management and Social Sciences |
| Subject: | 85 business administration, organizational science |
| Programme: | Business Administration MSc (60644) |
| Link to this item: | https://purl.utwente.nl/essays/86510 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page