Leveraging unstructured call log data for customer churn prediction

Vo, Nhi N.Y.; Liu, Shaowu; Li, Xitong; Xu, Guandong

doi:10.1016/j.knosys.2020.106586

Cited by 61 publications

(21 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vo, et al [7] The customer churn prediction model is applied to the unstructured call center data This result shows that the developed model has a…”

Section: This Model Requires Trainingmentioning

confidence: 96%

“…The oversampling method is applied to handle the imbalance dataset where the feed-forward neural network has the overfitting problem in the training process. Random forest [4,5,7,8,13] has been highly used in the existing customer churns prediction due to its capacity to analyze the relations of features in the dataset. The random Forest method can handle the large dataset.…”

Section: Machine Learning Techniquesmentioning

confidence: 99%

“…Initially, data mining techniques are primarily applied to the churn prediction which is predicted by the telecom churners. For instance, neural networks and decision trees are applied to develop accurate churn prediction systems [6,7]. Various machine learning algorithm was applied to analyze the churning task like artificial neural networks, random forest, the statistical classifier (KNN), logistic regression, decision tree, support vector machines, and Naïve Bayes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Customer Churns Prediction Model Based on Machine Learning Techniques: A Systematic Review

Malikireddy¹,

Madhavi²

2021

Atlantis Highlights in Computer Sciences

View full text Add to dashboard Cite

The customer churn prediction model is required by many companies to predict the risk of customer churn and take necessary actions to prevent churn. Recently, machine-learning techniques are highly applied in customer churn prediction. In this paper, machine learning-based models are applied to the customer churn prediction, which is reviewed with their advantages and limitations. Random Forest methods were highly used in the existing customer churn prediction models due to their advantages of effectively analyzing the features in the data. Feature selection methods such as Particle Swarm Optimization (PSO) and Firefly algorithms were applied to improve the prediction process. The Ensemble classifiers of bagging and boosting of random forest are applied to the prediction of customer churns which achieves higher performance. Deep learning models such as Long Short Term Memory (LSTM) and Convolution Neural Network (CNN) were applied for prediction and achieves higher performance. Random forest model, LSTM, and CNN models have the limitations of overfitting problem of customer churn prediction. Feature selection techniques of PSO and firefly methods have the limitations of poor convergence and lower efficiency in handling the imbalanced dataset.

show abstract

“…Vo, et al [7] The customer churn prediction model is applied to the unstructured call center data This result shows that the developed model has a…”

Section: This Model Requires Trainingmentioning

confidence: 96%

Section: Machine Learning Techniquesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Customer Churns Prediction Model Based on Machine Learning Techniques: A Systematic Review

Malikireddy¹,

Madhavi²

2021

Atlantis Highlights in Computer Sciences

View full text Add to dashboard Cite

show abstract

“…However, the conventional approach of using single classifiers for churn prediction is ineffective. It should be improved, as various uncertainty factors such as customer service, network coverage, product quality, packaging prices, and reception quality can all contribute to customer churn [5].…”

Section: Introductionmentioning

confidence: 99%

Improving Customer Churn Classification with Ensemble Stacking Method

Awang¹,

Makhtar²,

Udin³

et al. 2021

IJACSA

View full text Add to dashboard Cite

Due to the high cost of acquiring new customers, accurate customer churn classification is critical in any company. The telecommunications industry has employed single classifiers to classify customer churn; however, the classification accuracy remains low. Nevertheless, combining several classifiers' decisions improves classification accuracy. This article attempts to enhance ensemble integration via stack generalisation. This paper proposed a stacking ensemble based on six different learning algorithms as the base-classifiers and tested on five different meta-model classifiers. We compared the performance of the proposed stacking ensemble model with single classifiers, bagging and boosting ensemble. The performances of the models were evaluated with accuracy, precision, recall and ROC criteria. The findings of the experiments demonstrated that the proposed stacking ensemble model resulted in the improvement of the customer churn classification. Based on the results of the experiments, it indicates that the prediction accuracy, precision, recall and ROC of the proposed stacking ensemble with MLP meta-model outperformed other single classifiers and ensemble methods for the customer churn dataset.

show abstract

“…The …ndings of the study indicate that best performance achived by RF and ADA boost with almost %96 accuracy and SVM with %94 accuracy. Some other recent machine learning approach on customer churn predictions are [12], [13], [14] and [15].…”

Section: Introductionmentioning

confidence: 99%

Predicting credit card customer churn using support vector machine based on Bayesian optimization

Ünlü¹

2021

Communications Faculty of Science University of Ankara Series A1Mathematics and Statistics

View full text Add to dashboard Cite

In this study, we have employed a hybrid machine learning algorithm to predict credit card customer churn. The proposed model is Support Vector Machine (SVM) with Bayesian Optimization (BO). BO is used to optimize the hyper-parameters of the SVM. Four di¤erent kernels are utilized. The hyper-parameters of the utilized kernels are calculated by the BO. The prediction power of the proposed models is compared by four di¤erent evaluation metrics. Used metrics are accuracy, precision, recall and F 1 -score. According to each metrics linear kernel has the highest performance. It has accuracy of %91. The worst performance achieved by sigmoid kernel which has accuracy of %84.

show abstract

Leveraging unstructured call log data for customer churn prediction

Cited by 61 publications

References 39 publications

Customer Churns Prediction Model Based on Machine Learning Techniques: A Systematic Review

Customer Churns Prediction Model Based on Machine Learning Techniques: A Systematic Review

Improving Customer Churn Classification with Ensemble Stacking Method

Predicting credit card customer churn using support vector machine based on Bayesian optimization

Contact Info

Product

Resources

About