Churn Prediction using Machine Learning-An Analytical CRM Application
M Kavitha Margret1, M Monishapriyadharshini2, S Nathies3, C Sriram4
1Ms. M. Kavitha Margret*, Assistant Professor in Sri Krishna College of Technology, Coimbatore, Tamil Nadu, India.
2Ms. M. Monishapriyadharshini, IV year CSE, Sri Krishna College of Technology, Coimbatore, Tamil Nadu, India.
3Mr. S. Nathies, IV year CSE, Sri Krishna College of Technology, Coimbatore, Tamil Nadu, India.
4Mr. C. Sriram, IV year CSE, Sri Krishna College of Technology, Coimbatore, Tamil Nadu, India.
Manuscript received on February 10, 2020. | Revised Manuscript received on February 23, 2020. | Manuscript published on March 10, 2020. | PP: 1948-1952 | Volume-9 Issue-5, March 2020. | Retrieval Number: E2931039520/2020©BEIESP | DOI: 10.35940/ijitee.E2931.039520
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: CRM represents (Customer Relationship Management).It is a classification of programming that covers many arrangement of utilizations that are intended to support organizations and furthermore to oversee huge numbers of the business forms like client information. CRM framework models incorporate stages worked to oversee advertising, deals, client support, and backing, all associated with assistance organizations work all the more viably. With a CRM framework, organizations can dissect client collaborations and improve their client connections. The data based forecast models utilizing AI systems have increased monstrous prevalence during the most recent couple of decades. These models have been applied in enormous number of areas like clinical conclusion, wrongdoing expectation, films rating, and so forth. Thus it is utilized in telecom industry where models of expectation have been applied for the forecast of not fulfilled clients who are probably going to change the administrations and furthermore the specialist organization. In telecom the money related expense of client agitate is tremendous henceforth numerous organizations have examined different variables, (for example, cost of the call, nature of the call, client assistance reaction time and so on.) utilizing different AI strategies. This work proposes different ML strategies for client agitate expectation.
Keywords: CRM, Telecom, churn, classification, Machine learning.
Scope of the Article: Machine learning.