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...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/16/8270 |
| _version_ | 1797411272877146112 |
|---|---|
| author | Fatima Enehezei Usman-Hamza Abdullateef Oluwagbemiga Balogun Luiz Fernando Capretz Hammed Adeleye Mojeed Saipunidzam Mahamad Shakirat Aderonke Salihu Abimbola Ganiyat Akintola Shuib Basri Ramoni Tirimisiyu Amosa Nasiru Kehinde Salahdeen |
| author_facet | Fatima Enehezei Usman-Hamza Abdullateef Oluwagbemiga Balogun Luiz Fernando Capretz Hammed Adeleye Mojeed Saipunidzam Mahamad Shakirat Aderonke Salihu Abimbola Ganiyat Akintola Shuib Basri Ramoni Tirimisiyu Amosa Nasiru Kehinde Salahdeen |
| author_sort | Fatima Enehezei Usman-Hamza |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T04:43:42Z |
| format | Article |
| id | doaj.art-1ff9347fff7e44cc8e372b18a44ac05a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T04:43:42Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1ff9347fff7e44cc8e372b18a44ac05a2023-12-03T13:18:13ZengMDPI AGApplied Sciences2076-34172022-08-011216827010.3390/app12168270Intelligent Decision Forest Models for Customer Churn PredictionFatima Enehezei Usman-Hamza0Abdullateef Oluwagbemiga Balogun1Luiz Fernando Capretz2Hammed Adeleye Mojeed3Saipunidzam Mahamad4Shakirat Aderonke Salihu5Abimbola Ganiyat Akintola6Shuib Basri7Ramoni Tirimisiyu Amosa8Nasiru Kehinde Salahdeen9Department of Computer Science, University of Ilorin, Ilorin 1515, NigeriaDepartment of Computer Science, University of Ilorin, Ilorin 1515, NigeriaDepartment of Electrical and Computer Engineering, Western University, London, ON N6A 5B9, CanadaDepartment of Computer Science, University of Ilorin, Ilorin 1515, NigeriaDepartment of Computer and Information Science, Universiti Teknologi PETRONAS, Seri Iskandar 32610, MalaysiaDepartment of Computer Science, University of Ilorin, Ilorin 1515, NigeriaDepartment of Computer Science, University of Ilorin, Ilorin 1515, NigeriaDepartment of Computer and Information Science, Universiti Teknologi PETRONAS, Seri Iskandar 32610, MalaysiaDepartment of Computer Science, University of Ilorin, Ilorin 1515, NigeriaDepartment of Computer Science, University of Ilorin, Ilorin 1515, NigeriaCustomer 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.https://www.mdpi.com/2076-3417/12/16/8270telecommunicationcustomer churndecision forestmachine learningensemble |
| spellingShingle | Fatima Enehezei Usman-Hamza Abdullateef Oluwagbemiga Balogun Luiz Fernando Capretz Hammed Adeleye Mojeed Saipunidzam Mahamad Shakirat Aderonke Salihu Abimbola Ganiyat Akintola Shuib Basri Ramoni Tirimisiyu Amosa Nasiru Kehinde Salahdeen Intelligent Decision Forest Models for Customer Churn Prediction Applied Sciences telecommunication customer churn decision forest machine learning ensemble |
| title | Intelligent Decision Forest Models for Customer Churn Prediction |
| title_full | Intelligent Decision Forest Models for Customer Churn Prediction |
| title_fullStr | Intelligent Decision Forest Models for Customer Churn Prediction |
| title_full_unstemmed | Intelligent Decision Forest Models for Customer Churn Prediction |
| title_short | Intelligent Decision Forest Models for Customer Churn Prediction |
| title_sort | intelligent decision forest models for customer churn prediction |
| topic | telecommunication customer churn decision forest machine learning ensemble |
| url | https://www.mdpi.com/2076-3417/12/16/8270 |
| work_keys_str_mv | AT fatimaenehezeiusmanhamza intelligentdecisionforestmodelsforcustomerchurnprediction AT abdullateefoluwagbemigabalogun intelligentdecisionforestmodelsforcustomerchurnprediction AT luizfernandocapretz intelligentdecisionforestmodelsforcustomerchurnprediction AT hammedadeleyemojeed intelligentdecisionforestmodelsforcustomerchurnprediction AT saipunidzammahamad intelligentdecisionforestmodelsforcustomerchurnprediction AT shakirataderonkesalihu intelligentdecisionforestmodelsforcustomerchurnprediction AT abimbolaganiyatakintola intelligentdecisionforestmodelsforcustomerchurnprediction AT shuibbasri intelligentdecisionforestmodelsforcustomerchurnprediction AT ramonitirimisiyuamosa intelligentdecisionforestmodelsforcustomerchurnprediction AT nasirukehindesalahdeen intelligentdecisionforestmodelsforcustomerchurnprediction |