An ensemble based approach using a combination of clustering and classification algorithms to enhance customer churn prediction in telecom industry

Bilal, Syed Fakhar; Almazroi, Abdulwahab Ali; Bashir, Saba; Khan, Farhan Hassan; Almazroi, Abdulaleem Ali

doi:10.7717/peerj-cs.854

Cited by 27 publications

(16 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2021) 26 0.9300 0.8110 – – – – Bilal et al . (2022) 27 0.9243 0.7181 – – 0.9470 0.8063 Karuppaiah and Gopalan (2021) 28 0.8900 – – – – Rabbah et al . (2022) 29 , – – 0.8350 0.8190 – – Karamollaoglu et al .…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

An efficient churn prediction model using gradient boosting machine and metaheuristic optimization

AlShourbaji,

Helian,

Sun

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Customer churn remains a critical challenge in telecommunications, necessitating effective churn prediction (CP) methodologies. This paper introduces the Enhanced Gradient Boosting Model (EGBM), which uses a Support Vector Machine with a Radial Basis Function kernel (SVMRBF) as a base learner and exponential loss function to enhance the learning process of the GBM. The novel base learner significantly improves the initial classification performance of the traditional GBM and achieves enhanced performance in CP-EGBM after multiple boosting stages by utilizing state-of-the-art decision tree learners. Further, a modified version of Particle Swarm Optimization (PSO) using the consumption operator of the Artificial Ecosystem Optimization (AEO) method to prevent premature convergence of the PSO in the local optima is developed to tune the hyper-parameters of the CP-EGBM effectively. Seven open-source CP datasets are used to evaluate the performance of the developed CP-EGBM model using several quantitative evaluation metrics. The results showed that the CP-EGBM is significantly better than GBM and SVM models. Results are statistically validated using the Friedman ranking test. The proposed CP-EGBM is also compared with recently reported models in the literature. Comparative analysis with state-of-the-art models showcases CP-EGBM's promising improvements, making it a robust and effective solution for churn prediction in the telecommunications industry.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Bilal et al . 27 introduced a CP model based on hybrid clustering and classification methods to predict customer churn from two publicly available datasets. The results showed that this model is more robust than the other existing models in the literature.…”

Section: Literature Reviewmentioning

confidence: 99%

An efficient churn prediction model using gradient boosting machine and metaheuristic optimization

AlShourbaji,

Helian,

Sun

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In terms of model improvement, numerous scholars have adopted ensemble learning methods: S. De constructed a novel stacked framework based on various basic data mining algorithms [25]. Fakhar Bilal and Xiahou each adopted an ensemble strategy of clustering before classification [26,27]. Karuppaiah used a stacking method based on Bayesian, gradient boosting trees, and support vector machines to build models [28].…”

Section: Related Workmentioning

confidence: 99%

Enhancing Game Customer Churn Prediction with a Stacked Ensemble Learning Model

Guo,

Xiong,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

With the rapid growth of mobile internet and smart devices, China's mobile game market has become highly competitive. Game companies face increasing costs in promoting games and acquiring new customers. In response, this paper proposes a stack-based model for game customer churn prediction. This model utilizes a comprehensive set of user features, including static, dynamic, and social network data extracted from game logs. To correct the imbalance between positive and negative examples in our dataset, we applied the Neighborhood Cleaning Rule (NCL). We then constructed the model using a stacking approach that integrates multiple machine learning models into a cohesive binary classification framework. This method systematically predicts customer churn by processing these features. Our approach was rigorously tested on a large-scale real-world dataset, comparing it against nine standard baseline methods. The results reveal that the stack-based model significantly outperforms these methods, achieving a prediction accuracy of 94%.

show abstract

“…According to Singh & Sivasankar (2019), Bagging could achieve a prediction accuracy of over 0.80. Moreover, the study by Bilal et al (2022) The study of Badawi et al (2019) provided evidence that the stacking model is preferable to the Bagging, boosting, and individual models in terms of accuracy and dependability in various situations. Bokaba et al (2022) conducted a study that demonstrated the superior performance of the stacking model compared to other models in terms of accuracy, precision, recall, and F1-score in predicting road traffic congestion.…”

Section: Supervised Machine Learningmentioning

confidence: 99%

Enhancing Conversions and Lead Scoring in Online Professional Education

Yim,

Khaw,

Lim

et al. 2024

IJOMFA

View full text Add to dashboard Cite

This study seeks to enhance lead conversion for online professional education providers by using supervised machine learning algorithms for lead conversion targeting and lead scoring, including Logistic Regression, K-Nearest Neighbors, Support Vector Machines, Naïve Bayes, Random Forst, Bagging, Boosting, and Stacking. A lead dataset was used to train and test the machine-learning models. The Recursive Feature Elimination (RFE) is used to establish a precise lead profile. The performance of the trained lead conversion models was evaluated and compared using the 10-Folds cross-validation method based on accuracy, precision, recall, and F1-score. The results show that Stacking is the best model with an accuracy of 0.9233, precision of 0.9391, and F1-score of 0.8939. Meanwhile, the Logistic Regression-based lead scoring model demonstrated promising potential for automating lead scoring. The results of the Logistic Regression-based lead scoring model achieved an accuracy of 0.9019, recall of 0.9019, precision of 0.9015, and F1-score of 0.9014. The optimal lead scoring threshold is 0.20, which stroked the optimal trade-off balance between accuracy, sensitivity, and specificity.

show abstract

An ensemble based approach using a combination of clustering and classification algorithms to enhance customer churn prediction in telecom industry

Cited by 27 publications

References 38 publications

An efficient churn prediction model using gradient boosting machine and metaheuristic optimization

An efficient churn prediction model using gradient boosting machine and metaheuristic optimization

Enhancing Game Customer Churn Prediction with a Stacked Ensemble Learning Model

Enhancing Conversions and Lead Scoring in Online Professional Education

Contact Info

Product

Resources

About