Customer relationship mining system for effective strategies formulation

Abstract

Purpose – The purpose of this paper is to propose a customer relationship mining system (CRMS) to analyze the data collected from franchisees and formulates a marketing strategy based on customer demand and behavior. Design/methodology/approach – The system makes use of cloud technology to collect and manage data among the franchisees. An integrated approach of association rule mining and the neural network technique is adopted to investigate customer behavioral patterns and to forecast sales demand, respectively. Findings – The significance and contribution of this paper are demonstrated by adopting the CRMS in the education industry in Hong Kong. The findings led to the identification of student learning intentions such as course preferences, and the forecasting of enrolment demand in terms of demand forecast. It is believed that better resources allocation can be achieved and an increase in customer satisfaction is foreseeable. Research limitations/implications – The proposed CRMS could be applied to various franchising industries for effective marketing strategy formulation. However, since the data in this study are extracted from a specific industry, modifications may be required before the CRMS can be applied to other franchising industries. Originality/value – This study presents a new application to convert data into useful knowledge, and provides useful insights for delivering strategic promotional plans under a franchising business model. Through the pilot study conducted in a franchising education center, the results demonstrate that the proposed CRMS is valuable in providing effective promotion to attract more customers, better preparation in resources allocation and more standardized methods to formulate marketing strategies in the franchising industry.