Dynamic customer churn prediction strategy for business intelligence using text analytics with evolutionary optimization algorithms

Pustokhina, Irina V.; Pustokhin, Denis A.; Rh, Aswathy; Jayasankar, T.; Jeyalakshmi, C.; Díaz, Vicente García; Shankar, K.

doi:10.1016/j.ipm.2021.102706

Cited by 29 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whereas λ signifies the constant value which defines the "inertial" displacement of plants, P i (||X i + X i−1 ||) denotes the pollination probability, i.e., the sunflower i pollinates with their nearby neighbor i − 1 generating a novel individual from the random place which varies dependent on all the distances amongst the flowers [21]. In detail, an individual nearby the sun proceeds lesser step from the local refinement searching but more distant individuals are commonly moving.…”

Section: Overview Of Sfo Algorithmmentioning

confidence: 99%

Blockchain Driven Metaheuristic Route Planning in Secure Vehicular Adhoc Networks

Hassine¹,

Alotaibi²,

Alsolai³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Nowadays, vehicular ad hoc networks (VANET) turn out to be a core portion of intelligent transportation systems (ITSs), that mainly focus on achieving continual Internet connectivity amongst vehicles on the road. The VANET was utilized to enhance driving safety and build an ITS in modern cities. Driving safety is a main portion of VANET, the privacy and security of these messages should be protected. In this aspect, this article presents a blockchain with sunflower optimization enabled route planning scheme (BCSFO-RPS) for secure VANET. The presented BCSFO-RPS model focuses on the identification of routes in such a way that vehicular communication is secure. In addition, the BCSFO-RPS model employs SFO algorithm with a fitness function for effectual identification of routes. Besides, the proposed BCSFO-RPS model derives an intrusion detection system (IDS) encompassing two processes namely feature selection and classification. To detect intrusions, correlation based feature selection (CFS) and kernel extreme machine learning (KELM) classifier is applied. The performance of the BCSFO-RPS model is tested using a series of experiments and the results reported the enhancements of the BCSFO-RPS model over other approaches with maximum accuracy of 98.70%.

show abstract

Section: Overview Of Sfo Algorithmmentioning

confidence: 99%

Blockchain Driven Metaheuristic Route Planning in Secure Vehicular Adhoc Networks

Hassine¹,

Alotaibi²,

Alsolai³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…Authors report that experiment results of proposed technique exhibit remarkable accuracy scores on three datasets. In [19], authors concentrate on metaheuristic optimization technique namely, chaotic pigeon to handle the customer churn by predicting it with long short-term memory network model. To show the effectiveness of the proposed model, authors perform experiments on there datasets.…”

Section: Literature Backgroundmentioning

confidence: 99%

The Effectiveness of Homogeneous Classifier Ensembles on Customer Churn Prediction in Banking, Insurance, and Telecommunication Sectors

Kilimci

2022

International Journal of Computational and Experimental Science and Engineering

View full text Add to dashboard Cite

The prediction of customer churn is a big challenging problem for companies in different sectors such as banking, telecommunication, and insurance. It is a crucial estimation for many businesses since obtaining new customers frequently costs more than holding present ones. For this reason, analysts and researchers are focus on to investigate reasons behind of customer churn analyzing behaviors of them. In this paper, an ensemble-based framework is proposed to predict the customer churn in various sectors, namely banking, insurance, and telecommunication. To demonstrate the effectiveness of proposed ensemble framework, k-NN, logistic regression, naïve Bayes, support vector machine, decision tree, random forest, multilayer perceptron algorithms are employed. Moreover, the effects of the inclusion of feature extraction process are investigated. Experiment results indicate that that random forest algorithm is capable to predict churn customers with 89.93% of accuracy in banking, 95.90% of accuracy in telecommunication, and 77.53% of accuracy in insurance sectors when feature extraction procedure is carried out.

show abstract

“…A few reasons for churn are dissatisfaction in services such as unattractive recharge plans, frequent call drops, insufficient bandwidth, frequent customer care calls, unreachable networks, and slow Internet speed. In general, several techniques are used to address the customer churn prediction such as statistical learning [ 2 ], machine learning [ 3 ], evolutionary optimization technique [ 4 ], and deep learning [ 5 ]. Boosting is an ensemble technique that attempts to create a robust classifier from several weak classifiers.…”

Section: Introductionmentioning

confidence: 99%

Clairvoyant: AdaBoost with Cost-Enabled Cost-Sensitive Classifier for Customer Churn Prediction

Thakkar

Desai

Ghosh³

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Customer churn prediction is one of the challenging problems and paramount concerns for telecommunication industries. With the increasing number of mobile operators, users can switch from one mobile operator to another if they are unsatisfied with the service. Marketing literature states that it costs 5–10 times more to acquire a new customer than retain an existing one. Hence, effective customer churn management has become a crucial demand for mobile communication operators. Researchers have proposed several classifiers and boosting methods to control customer churn rate, including deep learning (DL) algorithms. However, conventional classification algorithms follow an error-based framework that focuses on improving the classifier’s accuracy over cost sensitization. Typical classification algorithms treat misclassification errors equally, which is not applicable in practice. On the contrary, DL algorithms are computationally expensive as well as time-consuming. In this paper, a novel class-dependent cost-sensitive boosting algorithm called AdaBoostWithCost is proposed to reduce the churn cost. This study demonstrates the empirical evaluation of the proposed AdaBoostWithCost algorithm, which consistently outperforms the discrete AdaBoost algorithm concerning telecom churn prediction. The key focus of the AdaBoostWithCost classifier is to reduce false-negative error and the misclassification cost more significantly than the AdaBoost.

show abstract

Dynamic customer churn prediction strategy for business intelligence using text analytics with evolutionary optimization algorithms

Cited by 29 publications

References 18 publications

Blockchain Driven Metaheuristic Route Planning in Secure Vehicular Adhoc Networks

Blockchain Driven Metaheuristic Route Planning in Secure Vehicular Adhoc Networks

The Effectiveness of Homogeneous Classifier Ensembles on Customer Churn Prediction in Banking, Insurance, and Telecommunication Sectors

Clairvoyant: AdaBoost with Cost-Enabled Cost-Sensitive Classifier for Customer Churn Prediction

Contact Info

Product

Resources

About