Explainable AI Based Approach For Broadband Customers' Churn Prediction

被引:0
|
作者
Ciabattoni, Lucio [1 ,2 ]
Maiolatesi, Marco [2 ]
Mancinelli, Martina [2 ]
Di Tillo, Maria [2 ]
Fiandra, Riccardo [3 ]
Gerosa, Nicolo [3 ]
Trimeloni, Lorenzo [3 ]
Borghi, Matteo [3 ]
Bertolotti, Massimo [3 ]
机构
[1] Univ Politecn Marche, Dept Ind Engn, I-60131 Ancona, Italy
[2] Revolt Srl, Via Sandro Totti 11, I-60131 Ancona, Italy
[3] Sky Italia Srl, Via Monte Penice 7, I-20138 Milan, Italy
关键词
Broadband connection; Customer satisfaction; xAI; Churn rate; SERVICE;
D O I
10.1109/GEM61861.2024.10585597
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
In the digital era, where seamless connectivity is the lifeblood of modern society, broadband internet service providers face the dual challenge of meeting the ever-increasing demands of consumers while ensuring consistent and reliable Quality of Service (QoS). The quest for superior customer satisfaction and the reduction of churn rates have become paramount in an industry marked by intense competition. To face these pressing industry challenges, this paper presents an innovative Explainable Artificial Intelligence (xAI) algorithm designed for the dual purpose of predicting customer churn due to poor network quality while providing an elucidation of the underlying causal factors. The algorithm's deployment equips providers with a toolkit to take informed and proactive actions, thus enabling enhanced service quality management and customer retention strategies.
引用
收藏
页码:17 / 18
页数:2
相关论文
共 50 条
  • [31] An Enhanced Prediction of Ovarian Cancer based on Ensemble Classifier using Explainable AI
    Thakur, Gopal Kumar
    Kulkarni, Shridhar
    Kumar, K. Senthil
    Sudarsanam, P.
    Sreenivasulu, Meruva
    Reddy, Pundru Chandra Shaker
    2024 2ND WORLD CONFERENCE ON COMMUNICATION & COMPUTING, WCONF 2024, 2024,
  • [32] Explainable AI Based Neck Direction Prediction and Analysis During Head Impacts
    Shridevi, S.
    Elias, Susan
    IEEE ACCESS, 2024, 12 : 31399 - 31408
  • [33] Energy Consumption Prediction with Explainable AI: Proposal for a data-based methodology
    Mueller, Julian
    Schuchter, Florian
    Mercedes-Benz, Ag
    Frey, Georg
    ATP MAGAZINE, 2024, (08):
  • [34] ABC Based Neural Network Approach for Churn Prediction in Telecommunication Sector
    Paliwal, Priyanka
    Kumar, Divya
    INFORMATION AND COMMUNICATION TECHNOLOGY FOR INTELLIGENT SYSTEMS (ICTIS 2017) - VOL 2, 2018, 84 : 343 - 349
  • [35] Customer Churn Prediction Approach Based on LLM Embeddings and Logistic Regression
    Chajia, Meryem
    Nfaoui, El Habib
    FUTURE INTERNET, 2024, 16 (12)
  • [36] Customers Churn Prediction using Artificial Neural Networks (ANN) in Telecom Industry
    Khan, Yasser
    Shafiq, Shahryar
    Naeem, Abid
    Ahmed, Sheeraz
    Safwan, Nadeem
    Hussain, Sabir
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2019, 10 (09) : 132 - 142
  • [37] A New SVDD Approach to Reliable and Explainable AI
    Carlevaro, Alberto
    Mongelli, Maurizio
    IEEE INTELLIGENT SYSTEMS, 2022, 37 (02) : 55 - 68
  • [38] EXplainable AI (XAI) approach to image captioning
    Han, Seung-Ho
    Kwon, Min-Su
    Choi, Ho-Jin
    JOURNAL OF ENGINEERING-JOE, 2020, 2020 (13): : 589 - 594
  • [39] Towards Explainable Machine Learning for Bank Churn Prediction Using Data Balancing and Ensemble-Based Methods
    Tekouabou, Stephane C. K.
    Gherghina, Stefan Cristian
    Toulni, Hamza
    Mata, Pedro Neves
    Martins, Jose Moleiro
    MATHEMATICS, 2022, 10 (14)
  • [40] Performance of Explainable AI Methods in Asset Failure Prediction
    Jakubowski, Jakub
    Stanisz, Przemyslaw
    Bobek, Szymon
    Nalepa, Grzegorz J.
    COMPUTATIONAL SCIENCE, ICCS 2022, PT IV, 2022, : 472 - 485