An Intelligent Hybrid Scheme for Customer Churn Prediction Integrating Clustering and Classification Algorithms

Abstract

Nowadays, customer churn has been reflected as one of the main concerns in the processes of the telecom sector, as it affects the revenue directly. Telecom companies are looking to design novel methods to identify the potential customer to churn. Hence, it requires suitable systems to overcome the growing churn challenge. Recently, integrating different clustering and classification models to develop hybrid learners (ensembles) has gained wide acceptance. Ensembles are getting better approval in the domain of big data since they have supposedly achieved excellent predictions as compared to single classifiers. Therefore, in this study, we propose a customer churn prediction (CCP) based on ensemble system fully incorporating clustering and classification learning techniques. The proposed churn prediction model uses an ensemble of clustering and classification algorithms to improve CCP model performance. Initially, few clustering algorithms such as k-means, k-medoids, and Random are employed to test churn prediction datasets. Next, to enhance the results hybridization technique is applied using different ensemble algorithms to evaluate the performance of the proposed system. Above mentioned clustering algorithms integrated with different classifiers including Gradient Boosted Tree (GBT), Decision Tree (DT), Random Forest (RF), Deep Learning (DL), and Naive Bayes (NB) are evaluated on two standard telecom datasets which were acquired from Orange and Cell2Cell. The experimental result reveals that compared to the bagging ensemble technique, the stacking-based hybrid model (k-medoids-GBT-DT-DL) achieve the top accuracies of 96%, and 93.6% on the Orange and Cell2Cell dataset, respectively. The proposed method outperforms conventional state-of-the-art churn prediction algorithms.

Machine learning based customer churn prediction in home appliance rental business

“…Ensemble-based classification algorithms have been recently developed [ 50 – 52 ]. Recently, Liu R et al[ 47 ] proposed an ensemble learning technique fully incorporating clustering and classification algorithm for customer churn prediction. Another issue is class imbalance in customer churn prediction.…”

A Novel Approach for Customer Churn Prediction in Telecom using Machine Learning Models

“…This makes it possible for businesses to take proactive steps to keep consumers and lessen the effects of churn. Significant telecom churn prediction research by eminent academics in the field is summarised in this section [39], [40], [41], [42], [43], [44], [45], [46], [47].…”

“…Rencheng Liu et al [44] created ensemble-based customer churn prediction models employing telecom churn prediction datasets from Orange and Cell2Cell in their study. To normalise and cluster the data, they used unsupervised techniques such as k-means, k-medoids, and random clustering.…”

Customer retention and churn prediction in the telecommunication industry: a case study on a Danish university

“…Empirical research also supports this; for instance, Bain & Company reported that increasing customer retention rates by 5% can increase profits from 25 to 95% [ 12 ]. Globalization and access to communication technology have resulted in multiple alternatives, motivating customers to switch from one service provider to another [ 13 ]. Due to high competition, the effects of regulatory pricing intervention and consolidation [ 14 ], and the growing popularity of over-the-top (OTT) services, the telecommunication industry faces shrinking revenues and profitability.…”

“… XGBC, AdaBoost & ETC Recall & F1-Score IBM: LR, NB & XGBC A proposed combination of classifiers out- perform all in terms of accuracy. [ 13 ] Cell2cell & Orange DL, NB, DT, GBC, RF Acc., Precision, Ensemble classifiers out- Recall & F-score performs the single classification techniques. [ 17 ] IBM telco CNN Accuracy Proposed CNN model support businesses to predict CC by TPR of 95%.…”