Izvorni znanstveni članak
https://doi.org/10.2498/cit.1002134
A Constraint Guided Progressive Sequential Mining Waterfall Model for CRM
Bhawna Mallick
; Department of Computer Science & Engineering, Thapar University, Patiala, India
Deepak Garg
; Department of Computer Science & Engineering, Thapar University, Patiala, India
P. S. Grover
; Department of Computer Science & Engineering, GTBIT, Delhi, India
Sažetak
CRM has been realized as a core for the growth of any enterprise. This requires both the customer satisfaction and fulfillment of customer requirement, which can only be achieved by analyzing consumer behaviors. The data mining has become an effective tool since often the organizations have large databases of information on customers. However, the traditional data mining techniques have no relevant mechanism to provide guidance for business understanding, model selection and dynamic changes made in the databases. This article helps in understanding and maintaining the requirement of continuous data mining process for CRM in dynamic environment. A novel integrative model, Constraint Guided Progressive SequentialMiningWaterfall (CGPSMW) for knowledge discovery process is proposed. The key performance factors that include management of marketing, sales, knowledge, technology among others those are required for the successful implementation of CRM. We have studied how the sequential pattern mining performed on progressive databases instead of static databases in conjunction with these CRM performance indicators can result in highly efficient and effective useful patterns. This would further help in classification of customers which any enterprise should focus on to achieve its growth and benefit. An organization has limited number of resources that it can only use for valuable customers to reap the fruits of CRM. The different steps of the proposed CGP-SMW model give a detailed elaboration how to keep focus on these customers in dynamic scenarios.
Ključne riječi
customer relationship management; key performance indicators; data mining techniques; constraints; sequential patterns; progressive databases; incremental mining
Hrčak ID:
123177
URI
Datum izdavanja:
18.6.2014.
Posjeta: 1.608 *