Customer Churn Prediction Research Articles

Customer Churn Prediction in Banking Sector - A Hybrid Approach

Abstract: No institution wants to lose customers and would do anything to prevent it. But banks can’t do anything about customer churn unless they predict it first. Predicting customer churn will help them to reach out to such customers and offer the assistance they need. With the support of precise and early churn prediction, customer resource management, and customer experience teams can be more assertive and customer-focused. It has been reported that simply reaching out to customers early enough can prevent 11 percent of attrition. The problem remains about how to predict such behaviour. Surveys are difficult to undertake and not many are interested in answering them. Past data holds the required solution. We can predict the behaviour of present and future customers by using machine learning and data science techniques to learn from this past customer data. In this paper, we aim to conduct a comparative analysis of different churn prediction models for banking institutions. Then we would implement a hybrid approach with the considered advantages from each of the best performing models for a given cluster of the dataset, to get better results.

Supervised Learning Algorithms for Predicting Customer Churn with Hyperparameter Optimization

Abstract Churn risk is one of the most worrying issues in the telecommunications industry. The methods for predicting churn have been improved to a great extent by the remarkable developments in the word of artificial intelligence and machine learning. In this context, a comparative study of four machine learning models was conducted. The first phase consists of data preprocessing, followed by feature analysis. In the third phase, feature selection. Then, the data is split into the training set and the test set. During the prediction phase, some of the commonly used predictive models were adopted, namely k-nearest neighbor, logistic regression, random forest, and support vector machine. Furthermore, we used cross-validation on the training set for hyperparameter adjustment and for avoiding model overfitting. Next, the hyperparameters were adjusted to increase the models' performance. The results obtained on the test set were evaluated using the feature weights, confusion matrix, accuracy score, precision, recall, error rate, and f1 score. Finally, it was found that the support vector machine model outperformed the other prediction models with an accuracy equal to 96.92%. Keywords: Churn Prediction, Classification Algorithms, Hyperparameter Optimization, Machine Learning, Telecommunications.

A Novel Hybrid Forecasting Approach for Customers Churn in Banking Industry

Competitive markets and customers’ changing needs in the bank industry necessitate accurately predicting customers who may leave the firm in the near future. Consequently, creating an approach to predict precisely and identify churn-leading causes is a part of retention strategies in customer relationship management. The approach that has been utilized in this research to predict customer churn combines decision tree (DT) and multinomial regression (MR) to classify customers with no limitation of binary classification in the churn prediction context. A customer club dataset of a commercial bank case as a real churn problem is used in this study to benchmark the hybrid forecasting approach against its building blocks. The results showed that the hybrid forecasting approach outperformed DT and MR with an average accuracy of 87.66%, 90.74% micro-average, and 90.44% macro-average of AUC. Further analysis of the model performance per class indicated that the hybrid approach’s misclassification error for the churn class decreased significantly, which is the most costly error in churn problems. Moreover, due to the structure of hybrid forecasting approach, more interoperability is obtained by assessing the impact of features in different segments, resulting in transforming them into actionable insights. The proposed approach is applied to the banking industry to prevent financial loss by detecting leading churn causes. Accordingly, after predicting the risk of customer churn, marketers and managers can determine appropriate actions that will have the most significant retention impact on each customer by applying proactive retention marketing.

Improve customer churn prediction through the proposed PCA-PSO-K means algorithm in the communication industry

Improve customer churn prediction through the proposed PCA-PSO-K means algorithm in the communication industry

Machine Learning to Develop Credit Card Customer Churn Prediction

The credit card customer churn rate is the percentage of a bank’s customers that stop using that bank’s services. Hence, developing a prediction model to predict the expected status for the customers will generate an early alert for banks to change the service for that customer or to offer them new services. This paper aims to develop credit card customer churn prediction by using a feature-selection method and five machine learning models. To select the independent variables, three models were used, including selection of all independent variables, two-step clustering and k-nearest neighbor, and feature selection. In addition, five machine learning prediction models were selected, including the Bayesian network, the C5 tree, the chi-square automatic interaction detection (CHAID) tree, the classification and regression (CR) tree, and a neural network. The analysis showed that all the machine learning models could predict the credit card customer churn model. In addition, the results showed that the C5 tree machine learning model performed the best in comparison with the three developed models. The results indicated that the top three variables needed in the development of the C5 tree customer churn prediction model were the total transaction count, the total revolving balance on the credit card, and the change in the transaction count. Finally, the results revealed that merging the multi-categorical variables into one variable improved the performance of the prediction models.

Analysis and Prediction of Telecom Customer Churn based on Machine Learning

As the telecommunications market becomes increasingly saturated, major operators are facing an increasingly severe problem of soaring customer churn rates. How to identify high-risk churn customers is the most concerned issue for operators. Thanks to the rapid development of pattern recognition technology, existing machine learning algorithms provide key technical support for telecom customer churn prediction. However, how to choose an appropriate forecasting method combined with the characteristics of the application data is still an open question. To this end, based on the analysis and comparison of the feature correlation between telecom customer data and churn, this paper compares the differences in the prediction results of different machine algorithms, so as to choose the method that best fits the characteristics of the application data to build the final customer churn prediction model. Specifically, the Spearman correlation coefficient is used to calculate the correlation between variables in the dataset, the random forest algorithm is used to score the importance of all variables, and the prediction generated by the gradient boosting tree algorithm is introduced. Finally, the gradient boosting tree algorithm is evaluated by five performance indicators: precision rate, recall rate, precision rate, F1 score and AUC (Area under the ROC curve).

Predicting Churn of Credit Card Customers Using Machine Learning and AutoML

Nowadays, a major concern for most retail banks is the risk that originates from customer fluctuation and that increases the cost of almost every financial product. In this work, the authors compared different approaches and algorithms to predict the relevant features that affect the customer churn, which means we can find ways to reduce the customer churn and create financial inclusion. This research was conducted by applying different machine learning techniques like decision tree classifier, random forest classifier, AdaBoost classifier, extreme gradient boosting, and balancing data with random under-sampling and random oversampling. The authors have also implemented AutoML to further compare different models and improve the accuracy of the model to predict customer churn. It was observed that applying AutoML highest accuracy model gave the accuracy of 97.53% in comparison to that of the decision tree classifier, which was 93.48% with the use of low processing power. Important features were ‘total transaction amount' and ‘total transaction count' to predict customer churn for a given dataset.

XAI for Churn Prediction in B2B Models: A Use Case in an Enterprise Software Company

The literature related to Artificial Intelligence (AI) models and customer churn prediction is extensive and rich in Business to Customer (B2C) environments; however, research in Business to Business (B2B) environments is not sufficiently addressed. Customer churn in the business environment and more so in a B2B context is critical, as the impact on turnover is generally greater than in B2C environments. On the other hand, the data used in the context of this paper point to the importance of the relationship between customer and brand through the Contact Center. Therefore, the recency, frequency, importance and duration (RFID) model used to obtain the customer’s assessment from the point of view of their interactions with the Contact Center is a novelty and an additional source of information to traditional models based on purchase transactions, recency, frequency, and monetary (RFM). The objective of this work consists of the design of a methodological process that contributes to analyzing the explainability of AI algorithm predictions, Explainable Artificial Intelligence (XAI), for which we analyze the binary target variable abandonment in a B2B environment, considering the relationships that the partner (customer) has with the Contact Center, and focusing on a business software distribution company. The model can be generalized to any environment in which classification or regression algorithms are required.

An effective strategy for churn prediction and customer profiling

Customer churn prediction and profiling are two major economic concerns for many companies. Different learning approaches have been proposed, however the a priori choice of the most suitable model to perform both tasks remains non-trivial as it is highly dependent on the intrinsic characteristics of the churn data. Our study compares eight supervised machine learning methods combined with seven sampling approaches on thirteen public churn data sets. Our evaluations, reported in terms of area under the curve (AUC), explore the influence of rebalancing strategies and data properties on the performance of learning methods. We rely on the Nemenyi test and Correspondence Analysis as means of visualizing the association between models, rebalancing and data. This work identifies the most appropriate methods in an attrition context and proposes an effective pipeline based on an ensemble approach and deep autoencoders segmentation. Our strategy can enlighten marketing or human resources services on the behavioral patterns of customers and their attrition probability. The described experiments are fully reproducible and our proposal can be successfully applied to a wide range of churn-like datasets.

Proactive customer retention management in a non-contractual B2B setting based on churn prediction with random forests

Customer churn prediction enables companies to target customers at risk with proactive retention measures. We develop a churn prediction model for a non-contractual business-to-business (B2B) wholesale setting and apply it in a field study. Our experiment shows that compared to random targeting, contacting the customers with the highest predicted churn probabilities reduces churn in the population significantly. We demonstrate that this also entails a positive financial impact in terms of revenue development.In addition to validating B2B churn prediction and retention in the field, we contribute to the literature by identifying the most important features. On top of the common recency, frequency and monetary value features, we show that features specific to customer relationship management such as the recency of the last contact with a field representative are important. We provide a concept on how to integrate proactive churn management into operations by leveraging existing customer care processes.

Predicting customer churn: A systematic literature review

Churn prediction is an active topic for research and machine learning approaches have made significant contributions in this domain. Models built to address customer churn, aim to identify customers who are at a high risk of terminating services offered by a company. Hence, an effective machine learning model indirectly contributes to the revenue growth of an organization, by identifying “at risk” customers, well in advance. This improves the success rate of retention campaigns and reduces costs associated with churn. The aim of this study is to explore the state-of-the-art machine learning techniques used in churn prediction. A systematic literature review, that is driven by 5 research questions and rigorous quality assessment criteria, is presented. There are 38 primary studies that are selected out of 420 studies published between 2018 and 2021. The review identifies popular machine learning techniques used in churn prediction and provides directions for future research. Firstly, the study finds that churn models lack generalization capability across industry domains. Hence, it identifies a need for researchers to explore techniques that extend beyond model experimentation, to improve efficiency of classifiers across domains. Secondly, it is observed that the traditional approaches to churn prediction depend significantly on demographic, product-usage, and revenue features alone. However, recent papers have integrated social network analysis-related features in churn models and achieved satisfactory results. Furthermore, there is a lack of scientific work that utilizes information-rich content of customer-company-interaction instances via email, chat conversations and other means. This area is the least explored. Thirdly, there is scope to investigate the effect of hybrid sampling strategies on model performance. This has not been extensively evaluated in literature. Lastly, there is no formal guideline on correct evaluation parameters to be used for models applied on imbalanced churn datasets. This is a grey area that requires greater attention.

Artificial Intelligence Based Customer Churn Prediction Model for Business Markets.

The introduction of artificial intelligence (AI) and machine learning (ML) technologies in recent years has resulted in improved company performance. Customer churn forecast is a difficult problem in many corporate sectors, particularly the telecommunications industry. Because customer churns have a direct impact on a company's total revenue, telecommunications firms have begun to develop 76 models to reduce churns at an earlier stage. Previous research has revealed that AI and ML models are effective CCP solutions. According to this viewpoint, this study proposes a unique AI-based CCP model for Telecommunication Business Markets (AICCP-TBM). The AICCP-TBM model's purpose is to control the existence of churners and non-churners in the telecom sector. The proposed AICCP-TBM model employs a Chaotic Salp Swarm Optimization-based Feature Selection (CSSO-FS) method for the best feature assortment. In addition, a Fuzzy Rule-based Classifier(FRC) is used to distinguish between client churners and non-churners. A technique known as Quantum Behaved Particle Swarm Optimization (QPSO) is used to pick the membership functions for the FRC model in order to improve the classification performance of the FRC model. The performance of the AICCP-TBM model is validated using a benchmark CCP dataset and the experimental results are reviewed from several angles. In relations of presentation, the imitation consequences demonstrated that the AICCP-TBM model surpassed the most recent state-of-the-art CPP models. The suggested AICCP-TBM method's comparative accuracy was thoroughly tested on the three datasets used. Using datasets 1-3, this technique obtained better levels of accuracy, with the maximum attainable values being 97.25 %, 97.5 % and 94.33 %. The simulation results for the AICCP-TBM model demonstrated improved prediction performance.

A Framework to Enhance Accuracy of Customer Churn Prediction in Telecom Industry

A Framework to Enhance Accuracy of Customer Churn Prediction in Telecom Industry

Bank Customer Churn Based on Different Models, Oversampling, and Encoding Methods

Customer churn prediction (CCP) is one of the cornerstones of Customer Relationship Management (CRM), in which one seeks to forecast whether or not a customer will quit the organization. Currently, plenty of algorithmic focuses on CCP. To fill the gap in the current study, this paper builds different models to predict bank user churn based on data from Kaggle. Specifically, we investigate the difference between models with and without oversampling, as well as discuss the difference between models under different coding methods. According to the results, ‘smote’ does not necessarily improve the performance accuracy, one hot encoding is more effective than target encoding. Finally, after all aspects of comparison, the logistic regression model is more reliable in the future analysis of customer churn of commercial banks. These results offer a guideline for future bank customer churn prediction.

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

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.

Research on telecom customer churn prediction based on ensemble learning

Research on telecom customer churn prediction based on ensemble learning

Performance Evaluation of Various Classification Techniques for Customer Churn Prediction in E-commerce

It is always a challenge to predict the customers on the verge of churn accurately in e-commerce due to the complexity of features and dynamicity of data and develop effective churn prediction models to predict potential churners accurately. This paper presents an in-depth comparison between four machine learning techniques namely neural network, support vector machine, Naïve Bayes and random forest, and Adam deep learning technique, for predicting customer churn in e-commerce. The classification techniques are implemented on benchmarked Brazilian e-commerce dataset. For the feature selection, principal component analysis and neighborhood component analysis techniques have been used. A balanced dataset, consisting of 11224 samples, is taken for study. The performance of the developed models is evaluated using the performance metrics viz. accuracy, sensitivity, specificity, true positive value, and true negative value. It has been found that the random forest classifier for the features selected using the neighborhood component analysis technique gives the highest prediction accuracy of 99.35% in comparison to classifiers used in this work as well as classifiers used by previous researchers. Additionally, the accuracy of the classifiers for features selected using the neighborhood component analysis technique is higher as compared to the principal component analysis technique. In future, authors are working further to improve the performance of the developed model by incorporating more features as well as evaluation parameters and proposing new models using convolutional neural networks. The authors also intend to use more than one dataset for the training of the models in the future.

Development of fading channel patch based convolutional neural network models for customer churn prediction

Development of fading channel patch based convolutional neural network models for customer churn prediction

Intelligent Decision Forest Models for Customer Churn Prediction

Customer churn is a critical issue impacting enterprises and organizations, particularly in the emerging and highly competitive telecommunications industry. It is important to researchers and industry analysts interested in projecting customer behavior to separate churn from non-churn consumers. The fundamental incentive is a firm’s intent desire to keep current consumers, along with the exorbitant expense of gaining new ones. Many solutions have been developed to address customer churn prediction (CCP), such as rule-based and machine learning (ML) solutions. However, the issue of scalability and robustness of rule-based customer churn solutions is a critical drawback, while the imbalanced nature of churn datasets has a detrimental impact on the prediction efficacy of conventional ML techniques in CCP. As a result, in this study, we developed intelligent decision forest (DF) models for CCP in telecommunication. Specifically, we investigated the prediction performances of the logistic model tree (LMT), random forest (RF), and Functional Trees (FT) as DF models and enhanced DF (LMT, RF, and FT) models based on weighted soft voting and weighted stacking methods. Extensive experimentation was performed to ascertain the efficacy of the suggested DF models utilizing publicly accessible benchmark telecom CCP datasets. The suggested DF models efficiently distinguish churn from non-churn consumers in the presence of the class imbalance problem. In addition, when compared to baseline and existing ML-based CCP methods, comparative findings showed that the proposed DF models provided superior prediction performances and optimal solutions for CCP in the telecom industry. Hence, the development and deployment of DF-based models for CCP and applicable ML tasks are recommended.

Correction to: Predicting customer churn for platform businesses: using latent variables of variational autoencoder as consumers’ purchasing behavior

Correction to: Predicting customer churn for platform businesses: using latent variables of variational autoencoder as consumers’ purchasing behavior