Enhanced Churn Prediction in the Telecommunication Industry
Journal Title: International Journal of Innovative Research in Computer Science and Technology - Year 2020, Vol 8, Issue 2
Abstract
Prediction models are usually built by applying a supervised learning algorithm to historical data. This involves the use of data analytics system that uses real-time integration and dynamic real time responses data to detect churn risks. Subscribe are increasingly terminating their membership agreement with telecommunication companies through mobile number portability (MNP) in order to subscribe to another competitor companies. To model the Customer prediction, a Markov Chain Model will be used. The Markov model allows for more flexibility than most other potential models, and can incorporate variables such as non-constant retention rate, which is not possible in the simpler models. The model allows looking at individual customer relationships as well as averages, and its probabilistic nature makes the uncertainty apprehensible. The Markov Decision Process is also appealing, but since dynamic decisions along the lifetime of the customer will not be evaluated the Markov Chain is the simplest model that still meets the requirements. Each state in the Markov Chain will represent a person being a customer for one month, with an infinite number of states. The transition probability to move from one state to the next is equivalent to a customer retaining with the operator to the next month. A customer that has churned will be considered lost forever. Once the retention and churn rates are determined, the reference churn value for each customer will be computed. The churn rate will be calculated using MATLAB Monte Carlo simulations, running a large number of fictitious customer-company relationship processes, and extracting the results of the average customer. Using simulation approach gives better result than analytical methods, since an indefinite number of states make matrix algebra complicated. It also allows visualizing the distribution of the results more easily than with algebraic calculation. To the telecom companies the result of this analysis would improve the level at which they can predict customer churn, because, it will give insight on why a customer would choose to leave one telecommunication industry for another telecommunication industry. In other words, the cost of advertisement and loyalty programs as well as challenges face in retaining loyal customers would be identified. The researcher believes that the enhanced model for churn prediction developed from this study will lead to better retention strategy, improved telecom quality service, enhanced customer loyalty due to the improvement service from applying the information from this model. The study is also significant to researchers, behavioral scientist, business analysts as well as professionals in the computer science domain. The study will serve as a good reference material for research and contribute to the growing objective of developing enhanced model built on data mining techniques that can explain the churn behavior with more accuracy than using single methods.
Authors and Affiliations
Awodele Oludele, Adeniyi Ben, Ogbonna A. C. , Kuyoro S. O. , Ebiesuwa Seun
Keywords
Related Articles
- EP ID EP747844
- DOI 10.21276/ijircst.2020.8.2.1
- Views 95
- Downloads 0
Securing and Secrete Image Sharing Using Visual Cryptography Scheme
To verify identity of person his /her physical or behavioural characteristics can be use,this strategy is called as Biometrics. Preservation of privacy of digital biometric data such as iris,face images etc. which stored...
Performance of MIMO-OFDM Transmission System on Wireless Networks
A detailed study of the performance of MIMOOFDM transmission on WLAN physical layer specified in IEEE 802.11n, Wi-MAX (IEEE 802.16-2009) physical layer specified in 802.16 and LTE downlink physical channel (PDSCH) has be...
Methodologies and Techniques for Network Transmission with Security and Corrective Control
Remedial checks operation techniques can be used to raise the flexibility, to maximize the integration of new generators and to reduce the overall cost. As far as the uncertainties considered, the transmission network sh...
In India, There Are Social Divisions in Education
The variations for 6-14-year-old India children in primary school enrollment by gender across three socioeconomic divisions, namely bottom and top caste Hindus, and Muslims, are described and analyzed in this study. It a...
Laboratory Review for Stabilization of Soil in Kashmir VALLEY by Using Surkhi and Ceramic Tile Waste
Clay soil has been identified as a concern all around the world due to its swelling and shrinking qualities when it comes into touch with water. The load characteristics of soil are particularly low due to this clay feat...