Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Explainable AI-driven customer churn prediction: a multi-model ensemble approach with SHAP-based feature analysis.

Ali El Attar1, Mohammed El-Hajj1

  • 1Faculty of Computer Studies (FCS), Arab Open University (AOU), Beirut, Lebanon.

Frontiers in Artificial Intelligence
|February 26, 2026
PubMed
Summary

Related Concept Videos

Prediction Intervals01:03

Prediction Intervals

3.5K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y. 
3.5K
Multiple Regression01:25

Multiple Regression

4.2K
Multiple regression assesses a linear relationship between one response or dependent variable and two or more independent variables. It has many practical applications.
Farmers can use multiple regression to determine the crop yield based on more than one factor, such as water availability, fertilizer, soil properties, etc. Here, the crop yield is the response or dependent variable as it depends on the other independent variables. The analysis requires the construction of a scatter plot...
4.2K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Advanced behavioral malware detection: a comprehensive MLOps framework with federated learning and real-time drift detection.

Frontiers in artificial intelligenceยท2026
See all related articles

This study enhances customer churn prediction in telecommunications using machine learning. Gradient boosting models, particularly XGBoost, show superior performance, identifying contract type and tenure as key churn indicators for targeted retention strategies.

Area of Science:

  • Telecommunications
  • Machine Learning
  • Data Science

Background:

  • Customer churn poses significant challenges to telecommunications profitability.
  • Effective retention strategies are crucial for maintaining market share and revenue.

Purpose of the Study:

  • To develop and evaluate a machine learning framework for accurate customer churn prediction.
  • To identify key drivers of customer churn within the telecommunications sector.
  • To provide actionable insights for optimizing customer retention strategies.

Main Methods:

  • Utilized the Telco Customer Churn dataset (n = 7,043).
  • Implemented feature engineering and SMOTE oversampling.
  • Trained and evaluated seven machine learning models, including XGBoost, Random Forest, and Multi-layer Perceptron.
Keywords:
SHAP analysiscustomer churn predictioncustomer retentioncustomer segmentationexplainable AImachine learning

Related Experiment Videos

  • Employed SHAP analysis for model interpretation and customer segmentation.

    • Main Results:

    • Gradient boosting algorithms (XGBoost, LightGBM, Gradient Boosting) achieved the highest balanced performance (F1-score: 0.84).
    • XGBoost demonstrated superior discriminative ability (AUC-ROC: 0.932).
    • Contract type, tenure, and technical support were identified as primary churn predictors.
    • Optimized prediction threshold (0.528) balanced precision (0.90) and recall (0.91), reducing false negatives by 15%.

    Conclusions:

    • Machine learning, particularly gradient boosting, offers a robust approach to customer churn prediction in telecommunications.
    • Identifying key churn drivers enables the development of targeted and effective customer retention initiatives.
    • The findings support data-driven decision-making for telecom customer retention efforts.