Work

Enhancing Retail Transactions: A Data-Driven Recommendation Using Modified RFM Analysis and Association Rules Mining

Year: 2023

Type: article

Abstract: Retail transactions have become an integral part of the economic cycle of every country and even on a global scale. Retail transactions are a trade sector that has the potential to be developed continuously in the future. This research focused on building a specified and data-driven recommendation system based on customer-purchasing and product-selling behavior. Modified RFM analysis was used by adding two variables, namely periodicity and customer engagement index; clustering algorithm such as K-means clustering and Ward’s method; and association rules to determine the pattern of the cause–effect relationship on each transaction and four types of classifiers to apply and to validate the recommendation system. The results showed that based on customer behavior, it should be split into two groups: loyal and potential customers. In contrast, for product behavior, it also comprised three groups: bestseller, profitable, and VIP product groups. Based on the result, K-nearest neighbor is the most suitable classifier with a low chance of overfitting and a higher performance index.

Source: Applied Sciences

DOI: 10.3390/app131810057

Authors: Angela Hsiang-Ling Chen, Sebastian Gunawan

Institution: Chung Yuan Christian University

Language: English

Topic: Customer churn and segmentation

Subfield: Marketing

Field: Business, Management and Accounting

Domain: Social Sciences

Open Access status: gold

Estimated APC paid: $2,558

Funder: Ministry of Science and Technology, Taiwan