A prediction algorithm of telecom customer churn based on Bayesian network parameters learning under incomplete data
Aiming at prediction of telecom customer churn,a novel method was proposed to increase the prediction accuracy with the missing data based on the Bayesian network.This method used k-nearest neighbor algorithm to fill the missing data and adds two types of monotonic influence constraints into the pro...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2018-01-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2018018/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530330139328512 |
|---|---|
| author | Yuxiang ZHAO Guangyue LU Hanglong WANG Siwei LI |
| author_facet | Yuxiang ZHAO Guangyue LU Hanglong WANG Siwei LI |
| author_sort | Yuxiang ZHAO |
| collection | DOAJ |
| description | Aiming at prediction of telecom customer churn,a novel method was proposed to increase the prediction accuracy with the missing data based on the Bayesian network.This method used k-nearest neighbor algorithm to fill the missing data and adds two types of monotonic influence constraints into the process of learning Bayesian network parameter.Simulations and actual data analysis demonstrate that the proposed algorithm obtains higher prediction accuracy of churn customers with the loss of less cost prediction accuracy of loyal customers,outperforms the classic expectation maximization algorithm. |
| format | Article |
| id | doaj-art-e0b57fafff1c4029bcaa72456e88a1f6 |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2018-01-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-e0b57fafff1c4029bcaa72456e88a1f62025-01-15T03:05:21ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012018-01-0134526059597518A prediction algorithm of telecom customer churn based on Bayesian network parameters learning under incomplete dataYuxiang ZHAOGuangyue LUHanglong WANGSiwei LIAiming at prediction of telecom customer churn,a novel method was proposed to increase the prediction accuracy with the missing data based on the Bayesian network.This method used k-nearest neighbor algorithm to fill the missing data and adds two types of monotonic influence constraints into the process of learning Bayesian network parameter.Simulations and actual data analysis demonstrate that the proposed algorithm obtains higher prediction accuracy of churn customers with the loss of less cost prediction accuracy of loyal customers,outperforms the classic expectation maximization algorithm.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2018018/Bayesian networkparameter learningdata missingnearest neighbor algorithmqualitative constraint |
| spellingShingle | Yuxiang ZHAO Guangyue LU Hanglong WANG Siwei LI A prediction algorithm of telecom customer churn based on Bayesian network parameters learning under incomplete data Dianxin kexue Bayesian network parameter learning data missing nearest neighbor algorithm qualitative constraint |
| title | A prediction algorithm of telecom customer churn based on Bayesian network parameters learning under incomplete data |
| title_full | A prediction algorithm of telecom customer churn based on Bayesian network parameters learning under incomplete data |
| title_fullStr | A prediction algorithm of telecom customer churn based on Bayesian network parameters learning under incomplete data |
| title_full_unstemmed | A prediction algorithm of telecom customer churn based on Bayesian network parameters learning under incomplete data |
| title_short | A prediction algorithm of telecom customer churn based on Bayesian network parameters learning under incomplete data |
| title_sort | prediction algorithm of telecom customer churn based on bayesian network parameters learning under incomplete data |
| topic | Bayesian network parameter learning data missing nearest neighbor algorithm qualitative constraint |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2018018/ |
| work_keys_str_mv | AT yuxiangzhao apredictionalgorithmoftelecomcustomerchurnbasedonbayesiannetworkparameterslearningunderincompletedata AT guangyuelu apredictionalgorithmoftelecomcustomerchurnbasedonbayesiannetworkparameterslearningunderincompletedata AT hanglongwang apredictionalgorithmoftelecomcustomerchurnbasedonbayesiannetworkparameterslearningunderincompletedata AT siweili apredictionalgorithmoftelecomcustomerchurnbasedonbayesiannetworkparameterslearningunderincompletedata AT yuxiangzhao predictionalgorithmoftelecomcustomerchurnbasedonbayesiannetworkparameterslearningunderincompletedata AT guangyuelu predictionalgorithmoftelecomcustomerchurnbasedonbayesiannetworkparameterslearningunderincompletedata AT hanglongwang predictionalgorithmoftelecomcustomerchurnbasedonbayesiannetworkparameterslearningunderincompletedata AT siweili predictionalgorithmoftelecomcustomerchurnbasedonbayesiannetworkparameterslearningunderincompletedata |