Applications of Business Intelligence and Decision Making for the Customer Behaviour Analysis in Telecom Industry
Attili Venkata Ramana1, Annaluri Sreenivasa Rao2, E. Kesavulu Reddy3

1Dr. Attili Venkata Ramana, Associate Professor, Department of ECM, Sreenidhi Institute of Science and Technology, Hyderabad (Telangana), India.
2Dr. Annaluri Sreenivasa Rao, Assistant Professor, Department of IT, VNRVJIET, Hyderabad (Telangana), India.
3Dr. E. Kesavulu Reddy, Assistant Professor, Department of CS, SVUCMCS, SV University, Tirupathi (Andhra Pradesh), India.
Manuscript received on 26 March 2019 | Revised Manuscript received on 05 April 2019 | Manuscript Published on 27 April 2019 | PP: 688-693 | Volume-7 Issue-6S2 April 2019 | Retrieval Number: F11150476S219/2019©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: The decision-making (DM) systems play a vital role in the telecommunication industry to locate the customers at a particular time. The business data analysis techniques allows to find the customers data and produce analysis reports helps to implement best policies in a business environment. On the other hand, business intelligence (BI) tools ensure to predict and analyse the historical data with the current data, to predict the events of a business operation. This method seems to be more complex due to the involvement of large data from the millions of the customers. Using the data mining techniques along with DM and BI, the data can be processed effectively so as to deliver accurate decisions. In this work, application of customer leaving in the telecom industry is tested for prediction of customer behaviour using data mining techniques. Large number of data sets will be process from the telecom industry by introducing a unique method by combining hybrid genetic algorithm (GA) and particle swarm optimization (PSO) as HGAPSO, which allows extracting specific and useful data. By using the advantages of both the methods, one can accurately determine the decisions from the customer churn predictions using auxiliary vector classification method. The performance metrics in this work considered accuracy, true positive response rate (TPR), false positive rate (FPR), time complexity and receiver operating characteristics (ROC). The results from this work delivered high scalability using HGAPSO and well suited for predictions in the area of business analysis.
Keywords: CRM, BI, DM Systems, Attribute Selection, Customer Churn Prediction.
Scope of the Article: Artificial Intelligence