Multi-Behavior RFM Model Based on Improved SOM Neural Network Algorithm for Customer Segmentation

Abstract

Previous research on RFM (recency, frequency, and monetary value) models focused on only one type of user behavior data, i.e., the purchase behavior, without considering the interactions between users and items, such as clicking, favorite, and adding to cart. In this study, we propose a novel solution for deconstructing the multiple behaviors of consumers in a specific period and performing customer segmentation in an application promotion system called multi-behavior RFM (MB-RFM) based on the selforganizing map (SOM) algorithm. First, using the R, F, and M values, we analyzed the weight relationship between multiple behaviors of users and items using the superiority chart and entropy value methods. Each behavior ascribed to a customer was considered to be a part of MB-RFM model values, which were then used to classify customers using an improved SOM neural network. Subsequently, various promotion strategies were developed according to customer categories that can help application vendors in improving their application utilization and implementing targeted promotion strategies. To prove the effectiveness of the proposed method in sparse datasets, two real-world datasets were used to perform experiments, whose results demonstrated that the classification performance of our method was significantly more accurate.

A review on customer segmentation methods for personalized customer targeting in e-commerce use cases

“…For example, Hsieh (2004); Liu et al (2009) combine an RFM-analysis feature extraction with a SOM clustering to segment the customers in their case study. A recent example of an SOM approach is proposed by Liao et al (2022). They develop different marketing strategies for each segment for a retail use case.…”

“…. (2010),Sivaramakrishnan et al (2020),Krishna and Ravi (2021) ),Liu et al (2009),Liao et al (2022Liao et al ( ) (2004,Kang et al (2012),Bian et al (2013),Hong and Kim (2012),Ma et al (2016),Ramadas and Abraham (2018),Logesh et al (2020),Wang et al (2020),Barman and Chowdhury (2019),Griva et al , Y.-g.C. (2007),Jiang and Tuzhilin (2009),Rapecka and Dzemyda (2015),,Madzik and Shahin (2021),Dogan et al (2014),Abbasimehr and Shabani (2021),Simoes and Nogueira (2021) …”