Customer churn prediction by hybrid neural networks

Tsai, Chih‐Fong; Lu, Yu-Hsin

doi:10.1016/j.eswa.2009.05.032

Cited by 255 publications

(108 citation statements)

References 20 publications

Supporting

Mentioning

102

Contrasting

Unclassified

Order By: Relevance

“…Finally, linguistic variables are attached to the crisp output using the scaled function in Eqn. (10).…”

Section: Experimentation and Results Discussionmentioning

confidence: 99%

Enabling Customer Reward with a Hybrid Intelligent System (Case Study: JandJ Shopping Mall)

Uko¹,

Enyindah²,

Etuk³

2017

IJCA

View full text Add to dashboard Cite

A reward program (also known as a loyalty program) is a marketing technique often adopted by some companies to appreciate customers who frequently make purchases with such companies. Normally, this kind of program leads to giving a loyal customer gifts in forms of customer free merchandise, coupons, rewards and advance released products. In most situations, reward programs in these companies are often biased due to the mechanism employed in determining a loyal customer. Hence, this article introduces a method that uses two efficient artificial intelligent techniques namely; fuzzy logic and expert system (fuzzy expert system) to tackle the challenge of biasness in loyal customer selection. These Hybrid system worked efficiently when executed on Jane and Juliet (J&J) Shopping Mall's data and sales manager (domain expert) 's rule. It was able to fuzzify the different linguistic variables and also aggregated the firing rules (from the expert rule-base) to generate a crisp loyalty output after applying a fuzzy inference model. Object Oriented and Design (OOAD) Methodology was used in the design of the system and JAVA was used to implement it. Matlab's Simulink was also used in the simulation of the results.

show abstract

“…Finally, linguistic variables are attached to the crisp output using the scaled function in Eqn. (10).…”

Section: Experimentation and Results Discussionmentioning

confidence: 99%

Enabling Customer Reward with a Hybrid Intelligent System (Case Study: JandJ Shopping Mall)

Uko¹,

Enyindah²,

Etuk³

2017

IJCA

View full text Add to dashboard Cite

show abstract

“…Tsai C F et al [11] designed two mixed models to predict customers churn: the first model is the mixed model of neural network + neural network; the second model is the mixed model of self-organizing mapping + neural network. Pendharkar P C [12] proposed the neural network combined model based on genetic algorithm to model on the users churn.…”

Section: Backgroundsmentioning

confidence: 99%

Using Combined Model Approach for Churn Prediction in Telecommunication

Liu¹,

Zhang²,

Yang³

2017

Proceedings of the 3rd Annual International Conference on Electronics, Electrical Engineering and Information Science (EEEIS 20

View full text Add to dashboard Cite

Abstract:To solve the prediction problem of hybrid data in users' consumption information of telecommunication, the paper use the fuzzy K-Prototypes (FKP) and support vector machine (SVM) combined model to improve the accuracy of users churn prediction. In the combined model, FKP is adopted to cluster hybrid large data volume effectively, and then the samples nearby cluster center in each cluster as the input of SVM to promote the prediction efficiency. As shown in the experience validation results, the proposed FKP-SVM combined model has excellent performance in predicting churn, due to reduce the training time of hybrid large-scale data set and save system resources.

show abstract

“…In particular, Artificial Neural Networks (ANNs) methods, both supervised and unsupervised, represent the majority of studies in this branch. Hadden et al [5] [17]. Even though, ANNs are known to be stronger churn predictors than Decision Trees, they are known to have disadvantages such as early convergence or being stuck at local optima [5].…”

Section: Literature Reviewmentioning

confidence: 99%

Churn Detection and Prediction in Automotive Supply Industry

Karapinar

Altay

Kayakutlu

2016

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Abstract-Companies have both large certified enterprises and small unauthorized service providers as their competitors in the automotive supply industry. As technology related industries undergo more intensive competition, churn detection and prediction become essential to be precautious about leaving customers. The literature for churn detection offers numerous statistical and intelligent methods. In this study, Artificial Neural Networks and Decision Trees are applied to detect the churn in and analyze the validity of these methods for the automotive supply industry. The problem involves both categorical and continuous numerical decision inputs which cannot simultaneously fed into Decision Trees. In this case, continuous inputs should be divided into binary categorical ones by splitting into various intervals which are called buckets. Particle Swarm Optimization algorithm is implemented for finding optimal buckets for the churn problem data. Results indicate that while both algorithms are promising, the bucket tuning for Decision Trees complicate the churn detection process.

show abstract

Customer churn prediction by hybrid neural networks

Cited by 255 publications

References 20 publications

Enabling Customer Reward with a Hybrid Intelligent System (Case Study: JandJ Shopping Mall)

Enabling Customer Reward with a Hybrid Intelligent System (Case Study: JandJ Shopping Mall)

Using Combined Model Approach for Churn Prediction in Telecommunication

Churn Detection and Prediction in Automotive Supply Industry

Contact Info

Product

Resources

About