Customer Churn Prediction In Telecommunication Industry Using Machine Learning Classifiers

Mohammad, Nurul Izzati; Ismail, Saiful Adli; Kama, Nazri; Yusop, Othman Mohd; Azmi, Azri

doi:10.1145/3387168.3387219

Cited by 15 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…De Caigny et al [ 17 ] look into the value added by merging textual data with CCP techniques. It extends the previous study, which used a traditional CNN, to current ideal practises for textual data analysis in CCP and verifies an architecture for textual data analysis in CCP using real-world data from a European monetary services organisation.…”

Section: Existing Ccp Models For Telecommunication Sectormentioning

confidence: 99%

Artificial Intelligence Based Customer Churn Prediction Model for Business Markets

Banu

Neelakandan

Geetha

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The introduction of artificial intelligence (AI) and machine learning (ML) technologies in recent years has resulted in improved company performance. Customer churn forecast is a difficult problem in many corporate sectors, particularly the telecommunications industry. Because customer churns have a direct impact on a company's total revenue, telecommunications firms have begun to develop 76 models to reduce churns at an earlier stage. Previous research has revealed that AI and ML models are effective CCP solutions. According to this viewpoint, this study proposes a unique AI-based CCP model for Telecommunication Business Markets (AICCP-TBM). The AICCP-TBM model's purpose is to control the existence of churners and non-churners in the telecom sector. The proposed AICCP-TBM model employs a Chaotic Salp Swarm Optimization-based Feature Selection (CSSO-FS) method for the best feature assortment. In addition, a Fuzzy Rule-based Classifier(FRC) is used to distinguish between client churners and non-churners. A technique known as Quantum Behaved Particle Swarm Optimization (QPSO) is used to pick the membership functions for the FRC model in order to improve the classification performance of the FRC model. The performance of the AICCP-TBM model is validated using a benchmark CCP dataset and the experimental results are reviewed from several angles. In relations of presentation, the imitation consequences demonstrated that the AICCP-TBM model surpassed the most recent state-of-the-art CPP models. The suggested AICCP-TBM method's comparative accuracy was thoroughly tested on the three datasets used. Using datasets 1-3, this technique obtained better levels of accuracy, with the maximum attainable values being 97.25 %, 97.5 % and 94.33 %. The simulation results for the AICCP-TBM model demonstrated improved prediction performance.

show abstract

Section: Existing Ccp Models For Telecommunication Sectormentioning

confidence: 99%

Artificial Intelligence Based Customer Churn Prediction Model for Business Markets

Banu

Neelakandan

Geetha

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Tačnost najboljeg modela u ovom slučaju iznosi oko 82%. Prema [5] isti skup podataka korišćen je u velikom broju drugih radova poput [6,7,8], pri čemu se tačnost modela kreće u opsegu od 68% do 85%. Dostupnost podataka, koji su neophodni za kreiranje modela za predikciju odliva korisnika, je ograničena zbog poverljivosti i privatnosti podataka između telekomunikacionih operatora i njihovih korisnika [4].…”

Section: Rezultati I Analiza Rezultataunclassified

Predikcija Odliva Korisnika Telekomunikacionih Operatora Primenom Mašinskog Učenja

Janković¹,

Mladenović²,

Stefanović³

et al. 2022

Zbornik Radova Četrdesetog Simpozijuma O Novim Tehnologijama U Poštanskom I Telekomunikacionom Saobraćaju – Postel 2022

View full text Add to dashboard Cite

Kako bi prevenirao odliv korisnika, za telekomunikacionog operatora bilo bi korisno da sazna koji su to parametri koji najviše utiču na odlazak korisnika. Rad se bavi problemom predikcije budućeg odliva korisnika na osnovu istorijskih podataka u programskom jeziku Python. U cilju rešavanja ovog problema pronađen je odgovarajući, otvoreni skup podataka i izvršena istraživačka analiza podataka, kako bi se utvrdio stepen zavisnosti između svake nezavisne i zavisne varijable. Nezavisne varijable opisuju korisnika i servise koje je koristio, dok zavisna varijabla daje odgovor na pitanje: da li je korisnik do tog trenutka napustio operatora? Zatim su kreirani različiti klasifikacioni modeli mašinskog učenja korišćenjem nekih od algoritama implementiranih u Scikit-Learn biblioteci programskog jezika Python. Tačnost najboljih modela iznosila je preko 95%, što je za 10% više od tačnosti null modela, pa se može zaključiti da se predikacija odliva korisnika može uspešno vršiti korišćenjem mašinskog učenja, u programskom jeziku Python.

show abstract

“…In industrialised countries, the telecommunications sector has grown significantly [4]. The industry has grown extremely competitive due to the development of telecom service providers [5], [6]. Because of the increased competition brought on by the digital revolution, telecom providers are working harder than ever to provide consistent voice and data coverage in both urban and rural locations [6].…”

Section: Introductionmentioning

confidence: 99%

A Novel Approach for Customer Churn Prediction in Telecom using Machine Learning Models

Chaudhary¹,

Rizvi²,

Kumar³

et al. 2023

Preprint

View full text Add to dashboard Cite

For organizations across a range of industries, customer churn is a serious problem.Businesses must identify consumers who are in danger of leaving in order totake actions to keep them. By examining previous data and seeing trends indicatingclient behavior, machine learning provides a potent remedy for forecastingcustomer attrition. In this article, the investigation of the way machine learningtechniques can be utilized to forecast consumer attrition in the telecommunicationindustry has been done. The machine learning models decision trees and randomforests have been trained and assessed using IBM’s dataset of customer behaviorand demographics. These models are compared using performance parameterslike recall, accuracy, F1-score, and precision. According to chosen data, the randomforest model exceeds the competition with a remarkable accuracy of 96%.This study demonstrates the potential of machine learning in predicting customerturnover and offers insightful information for creating strategies that effectivelyretain customers.

show abstract

Customer Churn Prediction In Telecommunication Industry Using Machine Learning Classifiers

Cited by 15 publications

References 6 publications

Artificial Intelligence Based Customer Churn Prediction Model for Business Markets

Artificial Intelligence Based Customer Churn Prediction Model for Business Markets

Predikcija Odliva Korisnika Telekomunikacionih Operatora Primenom Mašinskog Učenja

A Novel Approach for Customer Churn Prediction in Telecom using Machine Learning Models

Contact Info

Product

Resources

About