Customer churns remains a key focus in this research, using artificial intelligence-based technique of machine learning. Research is based on the feature-based analysis four main features were used that are selected o...Customer churns remains a key focus in this research, using artificial intelligence-based technique of machine learning. Research is based on the feature-based analysis four main features were used that are selected on the basis of our customer churn to deduct the meaning full analysis of the data set. Data-set is taken from the Kaggle that is about the fine food review having more than half a million records in it. This research remains on feature based analysis that is further concluded using confusion matrix. In this research we are using confusion matrix to conclude the customer churn results. Such specific analysis helps e-commerce business for real time growth in their specific products focusing more sales and to analyze which product is getting outage. Moreover, after applying the techniques, Support Vector Machine and K-Nearest Neighbour perform better than the random forest in this particular scenario. Using confusion matrix for obtaining the results three things are obtained that are precision, recall and accuracy. The result explains feature-based analysis on fine food reviews, Amazon at customer churn Support Vector Machine performed better as in overall comparison.展开更多
Customer churn poses a significant challenge for the banking and finance industry in the United States, directly affecting profitability and market share. This study conducts a comprehensive comparative analysis of ma...Customer churn poses a significant challenge for the banking and finance industry in the United States, directly affecting profitability and market share. This study conducts a comprehensive comparative analysis of machine learning models for customer churn prediction, focusing on the U.S. context. The research evaluates the performance of logistic regression, random forest, and neural networks using industry-specific datasets, considering the economic impact and practical implications of the findings. The exploratory data analysis reveals unique patterns and trends in the U.S. banking and finance industry, such as the age distribution of customers and the prevalence of dormant accounts. The study incorporates macroeconomic factors to capture the potential influence of external conditions on customer churn behavior. The findings highlight the importance of leveraging advanced machine learning techniques and comprehensive customer data to develop effective churn prevention strategies in the U.S. context. By accurately predicting customer churn, financial institutions can proactively identify at-risk customers, implement targeted retention strategies, and optimize resource allocation. The study discusses the limitations and potential future improvements, serving as a roadmap for researchers and practitioners to further advance the field of customer churn prediction in the evolving landscape of the U.S. banking and finance industry.展开更多
In this study,the installation of an airlift pump with inner diameter of 102 mm and length of 5.64 m was utilized to consider the conveying process of non-spherical coal particles with density of 1340 kg/m3 and graini...In this study,the installation of an airlift pump with inner diameter of 102 mm and length of 5.64 m was utilized to consider the conveying process of non-spherical coal particles with density of 1340 kg/m3 and graining 25-44.5 mm.The test results revealed that the magnitude of increase in the solid transport rate due to the changes in the three tested parameters between compressed air velocity,submergence ratio,and feeding coal possibility was not the same,which are stand in range of 20%,75%,and 40%,respectively.Hence,creating the optimal airlift pump performance is highly dependent on submergence ratio.More importantly,we measured the solid volume fraction using the method of one-way valves in order to minimize the disadvantages of conventional devices,such as fast speed camera and conductivity ring sensor.The results confirmed that the volume fraction of the solid phase in the transfer process was always less than 12%.To validate present experimental data,the existing empirical correlations together with the theoretical equations related to the multiphase flow was used.The overall agreement between the theory and experimental solid delivery results was particularly good instead of the first stage of conveying process.This drawback can be corrected by omitting the role of friction and shear stress at low air income velocity.It was also found that the model developed by Kalenik failed to predict the performance of our airlift operation in terms of the mass flow rate of the coal particles.展开更多
The telecommunications industry is becoming increasingly aware of potential subscriber churn as a result of the growing popularity of smartphones in the mobile Internet era,the quick development of telecommunications ...The telecommunications industry is becoming increasingly aware of potential subscriber churn as a result of the growing popularity of smartphones in the mobile Internet era,the quick development of telecommunications services,the implementation of the number portability policy,and the intensifying competition among operators.At the same time,users'consumption preferences and choices are evolving.Excellent churn prediction models must be created in order to accurately predict the churn tendency,since keeping existing customers is far less expensive than acquiring new ones.But conventional or learning-based algorithms can only go so far into a single subscriber's data;they cannot take into consideration changes in a subscriber's subscription and ignore the coupling and correlation between various features.Additionally,the current churn prediction models have a high computational burden,a fuzzy weight distribution,and significant resource economic costs.The prediction algorithms involving network models currently in use primarily take into account the private information shared between users with text and pictures,ignoring the reference value supplied by other users with the same package.This work suggests a user churn prediction model based on Graph Attention Convolutional Neural Network(GAT-CNN)to address the aforementioned issues.The main contributions of this paper are as follows:Firstly,we present a three-tiered hierarchical cloud-edge cooperative framework that increases the volume of user feature input by means of two aggregations at the device,edge,and cloud layers.Second,we extend the use of users'own data by introducing self-attention and graph convolution models to track the relative changes of both users and packages simultaneously.Lastly,we build an integrated offline-online system for churn prediction based on the strengths of the two models,and we experimentally validate the efficacy of cloudside collaborative training and inference.In summary,the churn prediction model based on Graph Attention Convol展开更多
Background:Given the importance of customers as the most valuable assets of organizations,customer retention seems to be an essential,basic requirement for any organization.Banks are no exception to this rule.The comp...Background:Given the importance of customers as the most valuable assets of organizations,customer retention seems to be an essential,basic requirement for any organization.Banks are no exception to this rule.The competitive atmosphere within which electronic banking services are provided by different banks increases the necessity of customer retention.Methods:Being based on existing information technologies which allow one to collect data from organizations’databases,data mining introduces a powerful tool for the extraction of knowledge from huge amounts of data.In this research,the decision tree technique was applied to build a model incorporating this knowledge.Results:The results represent the characteristics of churned customers.Conclusions:Bank managers can identify churners in future using the results of decision tree.They should be provide some strategies for customers whose features are getting more likely to churner’s features.展开更多
Recently, peer-to-peer （P2P） search technique has become popular in the Web as an alternative to centralized search due to its high scalability and low deployment-cost. However, P2P search systems are known to suffe...Recently, peer-to-peer （P2P） search technique has become popular in the Web as an alternative to centralized search due to its high scalability and low deployment-cost. However, P2P search systems are known to suffer from the problem of peer dynamics, such as frequent node join/leave and document changes, which cause serious performance degradation. This paper presents the architecture of a P2P search system that supports full-text search in an overlay network with peer dynamics. This architecture, namely HAPS, consists of two layers of peers. The upper layer is a DHT （distributed hash table） network interconnected by some super peers （which we refer to as hubs）. Each hub maintains distributed data structures called search directories, which could be used to guide the query and to control the search cost. The bottom layer consists of clusters of ordinary peers （called providers）, which can receive queries and return relevant results. Extensive experimental results indicate that HAPS can perform searches effectively and efficiently. In addition, the performance comparison illustrates that HAPS outperforms a fiat structured system and a hierarchical unstructured system in the environment with peer dynamics.展开更多
To address the prominent problems faced by customer churn in telecom enterprise management, a telecom customer churn prediction model integrating GA-XGBoost and SHAP is proposed. By using the ADASYN algorithm for data...To address the prominent problems faced by customer churn in telecom enterprise management, a telecom customer churn prediction model integrating GA-XGBoost and SHAP is proposed. By using the ADASYN algorithm for data processing on the unbalanced sample set;based on the GA-XGBoost model, the XGBoost algorithm is used to construct the telecom customer churn prediction model, and the hyperparameters of the model are optimized by using the genetic algorithm. The experimental results show that compared with traditional machine learning methods such as GBDT, decision tree, KNN and single XGBoost model, the improved XGBoost model has better performance in recall, F1 value and AUC value;the GA-XGBoost model is integrated with SHAP framework to analyze and explain the important features affecting telecom customer churn, which is more in line with the telecom industry to predict customer the actual situation of churn.展开更多
In view of the fact that the prediction effect of influential financial customer churn in the Internet of Things environment is difficult to achieve the expectation,at the smart contract level of the blockchain,a cust...In view of the fact that the prediction effect of influential financial customer churn in the Internet of Things environment is difficult to achieve the expectation,at the smart contract level of the blockchain,a customer churn prediction framework based on situational awareness and integrating customer attributes,the impact of project hotspots on customer interests,and customer satisfaction with the project has been built.This framework introduces the background factors in the financial customer environment,and further discusses the relationship between customers,the background of customers and the characteristics of pre-lost customers.The improved Singular Value Decomposition(SVD)algorithm and the time decay function are used to optimize the search and analysis of the characteristics of pre-lost customers,and the key index combination is screened to obtain the data of potential lost customers.The framework will change with time according to the customer’s interest,adding the time factor to the customer churn prediction,and improving the dimensionality reduction and prediction generalization ability in feature selection.Logistic regression,naive Bayes and decision tree are used to establish a prediction model in the experiment,and it is compared with the financial customer churn prediction framework under situational awareness.The prediction results of the framework are evaluated from four aspects:accuracy,accuracy,recall rate and F-measure.The experimental results show that the context-aware customer churn prediction framework can be effectively applied to predict customer churn trends,so as to obtain potential customer data with high churn probability,and then these data can be transmitted to the company’s customer service department in time,so as to improve customer churn rate and customer loyalty through accurate service.展开更多
In the insurance sector, a massive volume of data is being generatedon a daily basis due to a vast client base. Decision makers and businessanalysts emphasized that attaining new customers is costlier than retainingex...In the insurance sector, a massive volume of data is being generatedon a daily basis due to a vast client base. Decision makers and businessanalysts emphasized that attaining new customers is costlier than retainingexisting ones. The success of retention initiatives is determined not only bythe accuracy of forecasting churners but also by the timing of the forecast.Previous works on churn forecast presented models for anticipating churnquarterly or monthly with an emphasis on customers’ static behavior. Thispaper’s objective is to calculate daily churn based on dynamic variations inclient behavior. Training excellent models to further identify potential churningcustomers helps insurance companies make decisions to retain customerswhile also identifying areas for improvement. Thus, it is possible to identifyand analyse clients who are likely to churn, allowing for a reduction in thecost of support and maintenance. Binary Golden Eagle Optimizer (BGEO)is used to select optimal features from the datasets in a preprocessing step.As a result, this research characterized the customer’s daily behavior usingvarious models such as RFM (Recency, Frequency, Monetary), MultivariateTime Series (MTS), Statistics-based Model (SM), Survival analysis (SA),Deep learning (DL) based methodologies such as Recurrent Neural Network(RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU),and Customized Extreme Learning Machine (CELM) are framed the problemof daily forecasting using this description. It can be concluded that all modelsproduced better overall outcomes with only slight variations in performancemeasures. The proposed CELM outperforms all other models in terms ofaccuracy (96.4).展开更多
Customer retention is one of the challenging issues in different business sectors,and variousfirms utilize customer churn prediction(CCP)process to retain existing customers.Because of the direct impact on the company ...Customer retention is one of the challenging issues in different business sectors,and variousfirms utilize customer churn prediction(CCP)process to retain existing customers.Because of the direct impact on the company revenues,particularly in the telecommunication sector,firms are needed to design effective CCP models.The recent advances in machine learning(ML)and deep learning(DL)models enable researchers to introduce accurate CCP models in the telecom-munication sector.CCP can be considered as a classification problem,which aims to classify the customer into churners and non-churners.With this motivation,this article focuses on designing an arithmetic optimization algorithm(AOA)with stacked bidirectional long short-term memory(SBLSTM)model for CCP.The proposed AOA-SBLSTM model intends to proficiently forecast the occurrence of CC in the telecommunication industry.Initially,the AOA-SBLSTM model per-forms pre-processing to transform the original data into a useful format.Besides,the SBLSTM model is employed to categorize data into churners and non-chur-ners.To improve the CCP outcomes of the SBLSTM model,an optimal hyper-parameter tuning process using AOA is developed.A widespread simulation analysis of the AOA-SBLSTM model is tested using a benchmark dataset with 3333 samples and 21 features.The experimental outcomes reported the promising performance of the AOA-SBLSTM model over the recent approaches.展开更多
As the banking industry gradually steps into the digital era of Bank 4.0,business competition is becoming increasingly fierce,and banks are also facing the problem of massive customer churn.To better maintain their cu...As the banking industry gradually steps into the digital era of Bank 4.0,business competition is becoming increasingly fierce,and banks are also facing the problem of massive customer churn.To better maintain their customer resources,it is crucial for banks to accurately predict customers with a tendency to churn.Aiming at the typical binary classification problem like customer churn,this paper establishes an early-warning model for credit card customer churn.That is a dual search algorithm named GSAIBAS by incorporating Golden Sine Algorithm(GSA)and an Improved Beetle Antennae Search(IBAS)is proposed to optimize the parameters of the CatBoost algorithm,which forms the GSAIBAS-CatBoost model.Especially,considering that the BAS algorithm has simple parameters and is easy to fall into local optimum,the Sigmoid nonlinear convergence factor and the lane flight equation are introduced to adjust the fixed step size of beetle.Then this improved BAS algorithm with variable step size is fused with the GSA to form a GSAIBAS algorithm which can achieve dual optimization.Moreover,an empirical analysis is made according to the data set of credit card customers from Analyttica official platform.The empirical results show that the values of Area Under Curve(AUC)and recall of the proposedmodel in this paper reach 96.15%and 95.56%,respectively,which are significantly better than the other 9 common machine learning models.Compared with several existing optimization algorithms,GSAIBAS algorithm has higher precision in the parameter optimization for CatBoost.Combined with two other customer churn data sets on Kaggle data platform,it is further verified that the model proposed in this paper is also valid and feasible.展开更多
The term “customer churn” is used in the industry of information and communication technology (ICT) to indicate those customers who are about to leave for a new competitor, or end their subscription. Predicting this...The term “customer churn” is used in the industry of information and communication technology (ICT) to indicate those customers who are about to leave for a new competitor, or end their subscription. Predicting this behavior is very important for real life market and competition, and it is essential to manage it. In this paper, three hybrid models are investigated to develop an accurate and efficient churn prediction model. The three models are based on two phases;the clustering phase and the prediction phase. In the first phase, customer data is filtered. The second phase predicts the customer behavior. The first model investigates the k-means algorithm for data filtering, and Multilayer Perceptron Artificial Neural Networks (MLP-ANN) for prediction. The second model uses hierarchical clustering with MLP-ANN. The third one uses self organizing maps (SOM) with MLP-ANN. The three models are developed based on real data then the accuracy and churn rate values are calculated and compared. The comparison with the other models shows that the three hybrid models outperformed single common models.展开更多
文摘Customer churns remains a key focus in this research, using artificial intelligence-based technique of machine learning. Research is based on the feature-based analysis four main features were used that are selected on the basis of our customer churn to deduct the meaning full analysis of the data set. Data-set is taken from the Kaggle that is about the fine food review having more than half a million records in it. This research remains on feature based analysis that is further concluded using confusion matrix. In this research we are using confusion matrix to conclude the customer churn results. Such specific analysis helps e-commerce business for real time growth in their specific products focusing more sales and to analyze which product is getting outage. Moreover, after applying the techniques, Support Vector Machine and K-Nearest Neighbour perform better than the random forest in this particular scenario. Using confusion matrix for obtaining the results three things are obtained that are precision, recall and accuracy. The result explains feature-based analysis on fine food reviews, Amazon at customer churn Support Vector Machine performed better as in overall comparison.
文摘Customer churn poses a significant challenge for the banking and finance industry in the United States, directly affecting profitability and market share. This study conducts a comprehensive comparative analysis of machine learning models for customer churn prediction, focusing on the U.S. context. The research evaluates the performance of logistic regression, random forest, and neural networks using industry-specific datasets, considering the economic impact and practical implications of the findings. The exploratory data analysis reveals unique patterns and trends in the U.S. banking and finance industry, such as the age distribution of customers and the prevalence of dormant accounts. The study incorporates macroeconomic factors to capture the potential influence of external conditions on customer churn behavior. The findings highlight the importance of leveraging advanced machine learning techniques and comprehensive customer data to develop effective churn prevention strategies in the U.S. context. By accurately predicting customer churn, financial institutions can proactively identify at-risk customers, implement targeted retention strategies, and optimize resource allocation. The study discusses the limitations and potential future improvements, serving as a roadmap for researchers and practitioners to further advance the field of customer churn prediction in the evolving landscape of the U.S. banking and finance industry.
基金supported by the European Research Council(Research Fund for Coal and Steel)under Grant Agreement number 800757.
文摘In this study,the installation of an airlift pump with inner diameter of 102 mm and length of 5.64 m was utilized to consider the conveying process of non-spherical coal particles with density of 1340 kg/m3 and graining 25-44.5 mm.The test results revealed that the magnitude of increase in the solid transport rate due to the changes in the three tested parameters between compressed air velocity,submergence ratio,and feeding coal possibility was not the same,which are stand in range of 20%,75%,and 40%,respectively.Hence,creating the optimal airlift pump performance is highly dependent on submergence ratio.More importantly,we measured the solid volume fraction using the method of one-way valves in order to minimize the disadvantages of conventional devices,such as fast speed camera and conductivity ring sensor.The results confirmed that the volume fraction of the solid phase in the transfer process was always less than 12%.To validate present experimental data,the existing empirical correlations together with the theoretical equations related to the multiphase flow was used.The overall agreement between the theory and experimental solid delivery results was particularly good instead of the first stage of conveying process.This drawback can be corrected by omitting the role of friction and shear stress at low air income velocity.It was also found that the model developed by Kalenik failed to predict the performance of our airlift operation in terms of the mass flow rate of the coal particles.
基金supported by National Key R&D Program of China(No.2022YFB3104500)Natural Science Foundation of Jiangsu Province(No.BK20222013)Scientific Research Foundation of Nanjing Institute of Technology(No.3534113223036)。
文摘The telecommunications industry is becoming increasingly aware of potential subscriber churn as a result of the growing popularity of smartphones in the mobile Internet era,the quick development of telecommunications services,the implementation of the number portability policy,and the intensifying competition among operators.At the same time,users'consumption preferences and choices are evolving.Excellent churn prediction models must be created in order to accurately predict the churn tendency,since keeping existing customers is far less expensive than acquiring new ones.But conventional or learning-based algorithms can only go so far into a single subscriber's data;they cannot take into consideration changes in a subscriber's subscription and ignore the coupling and correlation between various features.Additionally,the current churn prediction models have a high computational burden,a fuzzy weight distribution,and significant resource economic costs.The prediction algorithms involving network models currently in use primarily take into account the private information shared between users with text and pictures,ignoring the reference value supplied by other users with the same package.This work suggests a user churn prediction model based on Graph Attention Convolutional Neural Network(GAT-CNN)to address the aforementioned issues.The main contributions of this paper are as follows:Firstly,we present a three-tiered hierarchical cloud-edge cooperative framework that increases the volume of user feature input by means of two aggregations at the device,edge,and cloud layers.Second,we extend the use of users'own data by introducing self-attention and graph convolution models to track the relative changes of both users and packages simultaneously.Lastly,we build an integrated offline-online system for churn prediction based on the strengths of the two models,and we experimentally validate the efficacy of cloudside collaborative training and inference.In summary,the churn prediction model based on Graph Attention Convol
文摘Background:Given the importance of customers as the most valuable assets of organizations,customer retention seems to be an essential,basic requirement for any organization.Banks are no exception to this rule.The competitive atmosphere within which electronic banking services are provided by different banks increases the necessity of customer retention.Methods:Being based on existing information technologies which allow one to collect data from organizations’databases,data mining introduces a powerful tool for the extraction of knowledge from huge amounts of data.In this research,the decision tree technique was applied to build a model incorporating this knowledge.Results:The results represent the characteristics of churned customers.Conclusions:Bank managers can identify churners in future using the results of decision tree.They should be provide some strategies for customers whose features are getting more likely to churner’s features.
基金supported in part by the National Natural Science Foundation of China under Grant Nos. 60803003,60970124,60903038the Science and Technology Projects of Zhejiang Province under Grant No. 2008C14G2010007
文摘Recently, peer-to-peer （P2P） search technique has become popular in the Web as an alternative to centralized search due to its high scalability and low deployment-cost. However, P2P search systems are known to suffer from the problem of peer dynamics, such as frequent node join/leave and document changes, which cause serious performance degradation. This paper presents the architecture of a P2P search system that supports full-text search in an overlay network with peer dynamics. This architecture, namely HAPS, consists of two layers of peers. The upper layer is a DHT （distributed hash table） network interconnected by some super peers （which we refer to as hubs）. Each hub maintains distributed data structures called search directories, which could be used to guide the query and to control the search cost. The bottom layer consists of clusters of ordinary peers （called providers）, which can receive queries and return relevant results. Extensive experimental results indicate that HAPS can perform searches effectively and efficiently. In addition, the performance comparison illustrates that HAPS outperforms a fiat structured system and a hierarchical unstructured system in the environment with peer dynamics.
文摘To address the prominent problems faced by customer churn in telecom enterprise management, a telecom customer churn prediction model integrating GA-XGBoost and SHAP is proposed. By using the ADASYN algorithm for data processing on the unbalanced sample set;based on the GA-XGBoost model, the XGBoost algorithm is used to construct the telecom customer churn prediction model, and the hyperparameters of the model are optimized by using the genetic algorithm. The experimental results show that compared with traditional machine learning methods such as GBDT, decision tree, KNN and single XGBoost model, the improved XGBoost model has better performance in recall, F1 value and AUC value;the GA-XGBoost model is integrated with SHAP framework to analyze and explain the important features affecting telecom customer churn, which is more in line with the telecom industry to predict customer the actual situation of churn.
基金This work was supported by Shandong social science planning and research project in 2021(No.21CPYJ40).
文摘In view of the fact that the prediction effect of influential financial customer churn in the Internet of Things environment is difficult to achieve the expectation,at the smart contract level of the blockchain,a customer churn prediction framework based on situational awareness and integrating customer attributes,the impact of project hotspots on customer interests,and customer satisfaction with the project has been built.This framework introduces the background factors in the financial customer environment,and further discusses the relationship between customers,the background of customers and the characteristics of pre-lost customers.The improved Singular Value Decomposition(SVD)algorithm and the time decay function are used to optimize the search and analysis of the characteristics of pre-lost customers,and the key index combination is screened to obtain the data of potential lost customers.The framework will change with time according to the customer’s interest,adding the time factor to the customer churn prediction,and improving the dimensionality reduction and prediction generalization ability in feature selection.Logistic regression,naive Bayes and decision tree are used to establish a prediction model in the experiment,and it is compared with the financial customer churn prediction framework under situational awareness.The prediction results of the framework are evaluated from four aspects:accuracy,accuracy,recall rate and F-measure.The experimental results show that the context-aware customer churn prediction framework can be effectively applied to predict customer churn trends,so as to obtain potential customer data with high churn probability,and then these data can be transmitted to the company’s customer service department in time,so as to improve customer churn rate and customer loyalty through accurate service.
文摘In the insurance sector, a massive volume of data is being generatedon a daily basis due to a vast client base. Decision makers and businessanalysts emphasized that attaining new customers is costlier than retainingexisting ones. The success of retention initiatives is determined not only bythe accuracy of forecasting churners but also by the timing of the forecast.Previous works on churn forecast presented models for anticipating churnquarterly or monthly with an emphasis on customers’ static behavior. Thispaper’s objective is to calculate daily churn based on dynamic variations inclient behavior. Training excellent models to further identify potential churningcustomers helps insurance companies make decisions to retain customerswhile also identifying areas for improvement. Thus, it is possible to identifyand analyse clients who are likely to churn, allowing for a reduction in thecost of support and maintenance. Binary Golden Eagle Optimizer (BGEO)is used to select optimal features from the datasets in a preprocessing step.As a result, this research characterized the customer’s daily behavior usingvarious models such as RFM (Recency, Frequency, Monetary), MultivariateTime Series (MTS), Statistics-based Model (SM), Survival analysis (SA),Deep learning (DL) based methodologies such as Recurrent Neural Network(RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU),and Customized Extreme Learning Machine (CELM) are framed the problemof daily forecasting using this description. It can be concluded that all modelsproduced better overall outcomes with only slight variations in performancemeasures. The proposed CELM outperforms all other models in terms ofaccuracy (96.4).
文摘Customer retention is one of the challenging issues in different business sectors,and variousfirms utilize customer churn prediction(CCP)process to retain existing customers.Because of the direct impact on the company revenues,particularly in the telecommunication sector,firms are needed to design effective CCP models.The recent advances in machine learning(ML)and deep learning(DL)models enable researchers to introduce accurate CCP models in the telecom-munication sector.CCP can be considered as a classification problem,which aims to classify the customer into churners and non-churners.With this motivation,this article focuses on designing an arithmetic optimization algorithm(AOA)with stacked bidirectional long short-term memory(SBLSTM)model for CCP.The proposed AOA-SBLSTM model intends to proficiently forecast the occurrence of CC in the telecommunication industry.Initially,the AOA-SBLSTM model per-forms pre-processing to transform the original data into a useful format.Besides,the SBLSTM model is employed to categorize data into churners and non-chur-ners.To improve the CCP outcomes of the SBLSTM model,an optimal hyper-parameter tuning process using AOA is developed.A widespread simulation analysis of the AOA-SBLSTM model is tested using a benchmark dataset with 3333 samples and 21 features.The experimental outcomes reported the promising performance of the AOA-SBLSTM model over the recent approaches.
基金This work is supported by the National Natural Science Foundation of China(Nos.72071150,71871174).
文摘As the banking industry gradually steps into the digital era of Bank 4.0,business competition is becoming increasingly fierce,and banks are also facing the problem of massive customer churn.To better maintain their customer resources,it is crucial for banks to accurately predict customers with a tendency to churn.Aiming at the typical binary classification problem like customer churn,this paper establishes an early-warning model for credit card customer churn.That is a dual search algorithm named GSAIBAS by incorporating Golden Sine Algorithm(GSA)and an Improved Beetle Antennae Search(IBAS)is proposed to optimize the parameters of the CatBoost algorithm,which forms the GSAIBAS-CatBoost model.Especially,considering that the BAS algorithm has simple parameters and is easy to fall into local optimum,the Sigmoid nonlinear convergence factor and the lane flight equation are introduced to adjust the fixed step size of beetle.Then this improved BAS algorithm with variable step size is fused with the GSA to form a GSAIBAS algorithm which can achieve dual optimization.Moreover,an empirical analysis is made according to the data set of credit card customers from Analyttica official platform.The empirical results show that the values of Area Under Curve(AUC)and recall of the proposedmodel in this paper reach 96.15%and 95.56%,respectively,which are significantly better than the other 9 common machine learning models.Compared with several existing optimization algorithms,GSAIBAS algorithm has higher precision in the parameter optimization for CatBoost.Combined with two other customer churn data sets on Kaggle data platform,it is further verified that the model proposed in this paper is also valid and feasible.
文摘The term “customer churn” is used in the industry of information and communication technology (ICT) to indicate those customers who are about to leave for a new competitor, or end their subscription. Predicting this behavior is very important for real life market and competition, and it is essential to manage it. In this paper, three hybrid models are investigated to develop an accurate and efficient churn prediction model. The three models are based on two phases;the clustering phase and the prediction phase. In the first phase, customer data is filtered. The second phase predicts the customer behavior. The first model investigates the k-means algorithm for data filtering, and Multilayer Perceptron Artificial Neural Networks (MLP-ANN) for prediction. The second model uses hierarchical clustering with MLP-ANN. The third one uses self organizing maps (SOM) with MLP-ANN. The three models are developed based on real data then the accuracy and churn rate values are calculated and compared. The comparison with the other models shows that the three hybrid models outperformed single common models.
