A Study of Customer Segmentation Based on RFM Analysis and K-Means

Dwivedi, Shalabh; Singh, Amritpal

doi:10.1007/978-981-99-4071-4_27

Cited by 1 publication

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MBA and customer segmentation are prominent approaches to extracting insights from customer purchase behaviours [7]. However, the current body of literature reveals a lack of agreement regarding the most effective approaches and limitations related to the ability to apply findings to a broader population [8][9][10][11][12][13][14][15].…”

Section: Literature Reviewmentioning

confidence: 99%

“…In contrast, Kasem et al [9] emphasized the need for additional investigation into the scalability of their client profiling system. Dwivedi and Singh [10] proposed a complete segmentation strategy incorporating RFM, LTV, K-means, and neural networks. However, the authors expressed concerns about integrating several methods in dynamic situations.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Optimizing Decision-Making Through Customer-Centric Market Basket Analysis

Hoque,

Islam,

Mohtasim

2024

JOSA

View full text Add to dashboard Cite

In the realm of understanding consumer purchasing behaviors and refining decision-making across diverse sectors, Market Basket Analysis (MBA) emerges as a pivotal technique. Traditional algorithms, such as Apriori and Frequent Pattern Growth (FP-Growth), face challenges with computational efficiency, particularly under low minimal support settings, which precipitates an excess of weak association rules. This study introduces an innovative approach, termed Customer-Centric (CC)-MBA, which enhances the identification of robust association rules through the integration of consumer segmentation. By employing Recency, Frequency, and Monetary (RFM) analysis coupled with K-means clustering, customers are categorized based on their purchasing patterns, focusing on segments of substantial value. This targeted approach yields association rules that are not only more relevant but also more actionable compared to those derived from conventional MBA methodologies. The superiority of CC-MBA is demonstrated through its ability to discern more significant association rules, as evidenced by enhanced metrics of support and confidence. Additionally, the effectiveness of CC-MBA is further evaluated using lift and conviction metrics, which respectively measure the observed co-occurrence ratio to that expected by chance and the strength of association rules beyond random occurrences. The application of CC-MBA not only streamlines the analytical process by reducing computational demands but also provides more nuanced insights by prioritizing high-value customer segments. The practical implications of these findings are manifold; businesses can leverage this refined understanding to improve product positioning, devise targeted promotions, and tailor marketing strategies, thereby augmenting consumer satisfaction and facilitating revenue growth.

show abstract