Product Categorization for Social Marketing Applying the RFC Model and Data Science Techniques

Product Categorization for Social Marketing Applying the RFC Model and Data Science Techniques

Myint Zaw, Pichaya Tandayya
Copyright: © 2020 |Pages: 20
DOI: 10.4018/IJBAN.2020100104
(Individual Articles)
No Current Special Offers


Currently, it is the age of social market due to the growth of internet technologies. The marketers require the complete information of customer perspectives on products and services comparing with others. The RFM (recency, frequency, and monetary) model is a technique to measure a comparison of information, especially in traditional market analytics. Over the past decade, social market big data (SMBD), especially feedback, has been used to understand customer satisfaction. This paper proposes a new approach to classify the products from feedbacks, called the RFC (recency, frequency, and credit) model. The model focuses on the social market information and product categorization applying the natural language processing (NLP), opinion mining (OM), and data mining (DM) techniques.
Article Preview


The need to understand customer satisfaction on products and services is a basic business objective for designing better marketing strategies and improving their products and services effectively (Mohammadian & Makhani, 2016). These strategies can support marketing personnel and experts in making better decisions (Pépin, Kuntz, Blanchard, Guillet, & Suignard, 2017). Traditionally, marketing companies discover the patterns of customer behaviors by using the customers’ transactions in databases and data warehouse (Patel, Agrawal, & Josyula, 2016), (Birant, 2011). These can help identify company’s strategies based on customer satisfaction. In relation to that, the RFM (Recency, Frequency, and Monetary) model is a well-known methodology for processing and analyzing customer data in order to discover customer behavior patterns (Mohammadian & Makhani, 2016), (J. T. Wei, Lin, Yang, & Wu, 2016). A key aspect of the RFM model is to analyze customer behaviors about how recently a customer has purchased their products (R), how frequent the customer purchases their products (F), and how much the customer spends the total money for their products (M) (Iman Makhani, 2016), (Birant, 2011). The RFM model has been widely used, e.g., analyzing churn players for online games (Castro & Tsuzuki, 2015), classifying the bank customers (Patel et al., 2016), and sales and trade marketing strategies (Mohammadian & Makhani, 2016). Although the RFM model is in flavor of utilization in various companies for analyzing patterns of customer behaviors, its applications still focused on direct data and did not cover the customer satisfactions from indirect data. Nowadays, feedbacks are generated by on-line customers, who could provide sentiment information on products and services to marketers (Piao, Park, On, Choi, & Park, 2019).

One of well-known indirect data is Social Marketing Big Data (SMBD). It benefits from the growth of Internet technologies allowing the customers to share and feedback their opinions on a social media (Wong & Wei, 2018), (Nguyen & Jung, 2017). SMBD is streaming data, real-time generated by customers providing multi-view perspectives on a variety of media types (e.g., text as sentiment, image as vision, and video as human movement). It could be used to discover insight information to handle customer feedbacks and provide stimulations motivations for a marketing decision support system (Haddad & Baazaoui, 2018). Therefore, SMBD has an important role in the alternative marketing sustainability in understanding their company’s market, investigating for their customer satisfactions on products and services (Piao et al., 2019).

Even though SMBD appears to be helpful in the social marketing, it comes up with many constraints which concern high-speed velocity of content generation, a variety of types (such as text, image, and video), and diversified sources. Considering the textual data, it is often represented in unstructured forms which are only human-readable but cannot be bluntly interpreted by the machine (Bello-Orgaz, Jung, & Camacho, 2016), (Sivarajah, Kamal, Irani, & Weerakkody, 2017). Moreover, it also requires practitioners and experts to analyze SMBD. Therefore, there was a lack of automatic processes to analyze the data in exploiting SMBD.

Complete Article List

Search this Journal:
Volume 10: 1 Issue (2023)
Volume 9: 6 Issues (2022): 4 Released, 2 Forthcoming
Volume 8: 4 Issues (2021)
Volume 7: 4 Issues (2020)
Volume 6: 4 Issues (2019)
Volume 5: 4 Issues (2018)
Volume 4: 4 Issues (2017)
Volume 3: 4 Issues (2016)
Volume 2: 4 Issues (2015)
Volume 1: 4 Issues (2014)
View Complete Journal Contents Listing