Segmenting retail customers with an enhanced RFM and a hybrid regression/clustering method

Forskningsoutput: Kapitel i bok/konferenshandlingKonferensbidragVetenskapligPeer review

5 Citeringar (Scopus)
9 Nedladdningar (Pure)

Sammanfattning

Targeted marketing strategies use market segmentation for insight into the heterogeneity of the customer purchase lifecycle, but this often ignores the evolution of customer behavior over time causing retailers focus on unprofitable customers. By pairing the Recency, Frequency, Monetary scores with the Customer Lifetime Value model to segment customers of a medium-sized clothing and fashion accessory retailer in Kuwait. A modified regression algorithm investigates the customer purchase curve gaining knowledge from point-of-sales data to help the retailer make informed decisions. Clustering is by K-means and by Expectation Maximization. Cluster quality analysis reveals the former outperforms the latter to discover and suggest relevant market segments and appropriate marketing strategies.

OriginalspråkOdefinierat/okänt
Titel på gästpublikation2018 International Conference on Machine Learning and Data Engineering (iCMLDE)
FörlagIEEE
Sidor109–116
ISBN (elektroniskt)978-1-7281-0404-1
ISBN (tryckt)978-1-7281-0405-8
DOI
StatusPublicerad - 2018
MoE-publikationstypA4 Artikel i en konferenspublikation
EvenemangInternational Conference on Machine Learning and Data Engineering (iCMLDE) - 2018 International Conference on Machine Learning and Data Engineering (iCMLDE)
Varaktighet: 3 dec 20187 dec 2018

Konferens

KonferensInternational Conference on Machine Learning and Data Engineering (iCMLDE)
Period03/12/1807/12/18

Nyckelord

  • Clustering
  • RFM model
  • Retailing
  • Segmentation

Citera det här