Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Privacy-Preserving Customer Churn Prediction Model in the Context of Telecommunication Industry

Joydeb Kumar Sana, M Sohel Rahman, M Saifur Rahman

TL;DR

This work proposes a framework for privacy-preserving customer churn prediction (PPCCP) model in the cloud environment which is a combination of Generative Adversarial Networks (GANs) and adaptive Weight-of-Evidence (aWOE) which is a combination of GANs and aWOE.

Abstract

Data is the main fuel of a successful machine learning model. A dataset may contain sensitive individual records e.g. personal health records, financial data, industrial information, etc. Training a model using this sensitive data has become a new privacy concern when someone uses third-party cloud computing. Trained models also suffer privacy attacks which leads to the leaking of sensitive information of the training data. This study is conducted to preserve the privacy of training data in the context of customer churn prediction modeling for the telecommunications industry (TCI). In this work, we propose a framework for privacy-preserving customer churn prediction (PPCCP) model in the cloud environment. We have proposed a novel approach which is a combination of Generative Adversarial Networks (GANs) and adaptive Weight-of-Evidence (aWOE). Synthetic data is generated from GANs, and aWOE is applied on the synthetic training dataset before feeding the data to the classification algorithms. Our experiments were carried out using eight different machine learning (ML) classifiers on three openly accessible datasets from the telecommunication sector. We then evaluated the performance using six commonly employed evaluation metrics. In addition to presenting a data privacy analysis, we also performed a statistical significance test. The training and prediction processes achieve data privacy and the prediction classifiers achieve high prediction performance (87.1\% in terms of F-Measure for GANs-aWOE based Naïve Bayes model). In contrast to earlier studies, our suggested approach demonstrates a prediction enhancement of up to 28.9\% and 27.9\% in terms of accuracy and F-measure, respectively.

Privacy-Preserving Customer Churn Prediction Model in the Context of Telecommunication Industry

TL;DR

This work proposes a framework for privacy-preserving customer churn prediction (PPCCP) model in the cloud environment which is a combination of Generative Adversarial Networks (GANs) and adaptive Weight-of-Evidence (aWOE) which is a combination of GANs and aWOE.

Abstract

Data is the main fuel of a successful machine learning model. A dataset may contain sensitive individual records e.g. personal health records, financial data, industrial information, etc. Training a model using this sensitive data has become a new privacy concern when someone uses third-party cloud computing. Trained models also suffer privacy attacks which leads to the leaking of sensitive information of the training data. This study is conducted to preserve the privacy of training data in the context of customer churn prediction modeling for the telecommunications industry (TCI). In this work, we propose a framework for privacy-preserving customer churn prediction (PPCCP) model in the cloud environment. We have proposed a novel approach which is a combination of Generative Adversarial Networks (GANs) and adaptive Weight-of-Evidence (aWOE). Synthetic data is generated from GANs, and aWOE is applied on the synthetic training dataset before feeding the data to the classification algorithms. Our experiments were carried out using eight different machine learning (ML) classifiers on three openly accessible datasets from the telecommunication sector. We then evaluated the performance using six commonly employed evaluation metrics. In addition to presenting a data privacy analysis, we also performed a statistical significance test. The training and prediction processes achieve data privacy and the prediction classifiers achieve high prediction performance (87.1\% in terms of F-Measure for GANs-aWOE based Naïve Bayes model). In contrast to earlier studies, our suggested approach demonstrates a prediction enhancement of up to 28.9\% and 27.9\% in terms of accuracy and F-measure, respectively.

Paper Structure

This paper contains 24 sections, 3 equations, 13 figures, 14 tables.

Table of Contents

  1. Introduction
  2. Literature review
  3. Materials and Methodology
  4. Datasets
  5. Preprocessing
  6. Evaluation Measures
  7. Generative Adversarial Networks (GANs)
  8. Differential Privacy (DP)
  9. Training GANs With Differential Privacy
  10. Adaptive Weight-of-evidence (aWOE)
  11. Privacy Preserving GANs-aWOE CCP Framework
  12. Coding and Experimental Environment
  13. Results
  14. Performance Comparison Between aWOE and WOE DT method
  15. Experimental Results for Privacy-Preserving CCP model
  16. ...and 9 more sections

Figures (13)

  • Figure 1: Flowchart of Weight-of-Evidence (WOE), implemented in the mlencoders library.
  • Figure 2: Flowchart of Adaptive Weight-of-Evidence (aWOE).
  • Figure 3: Comprehensive block diagram of GANs-aWOE based Privacy-Preserving CCP Framework
  • Figure 4: Performance distribution of all classifiers for different $q$ values in terms of Accuracy on dataset-1
  • Figure 5: Performance distribution of all classifiers for different $q$ values in terms of F-measure on dataset-1
  • ...and 8 more figures