DOI QR코드

DOI QR Code

Predicting User Responses to Netflix's Account-Sharing Restriction Policy: A Machine Learning-Based Multiclass Classification Approach

넷플릭스 계정 공유 금지 정책에 대한 이용자 반응 예측: 기계학습 기반 다중 분류 접근

  • Boram Kwon (College of Business, The Catholic University of Korea) ;
  • Sun Me Choi (Electronics and Telecommunications Research Institute)
  • 권보람 (가톨릭대학교 경영학과) ;
  • 최선미 (한국전자통신연구원 기술전략연구센터)
  • Received : 2025.12.17
  • Accepted : 2026.01.31
  • Published : 2026.05.31

Abstract

This study developed a machine learning-based multi-class classification model to predict user responses to Netflix's account-sharing restriction policy. Using survey data from the Korea Press Foundation (n=681), user behaviors were categorized into five types: individual use, paying additional fees, stopping sharing, workaround-seeking, and service churn. Six algorithms were compared, with Random Forest achieving the highest performance (Accuracy 0.664, Macro F1-score 0.602) and high sensitivity in detecting churn (89%) and workaround-seeking (83%) groups. Permutation Importance and SHAP analyses revealed that subscription structure (32.6%) and sharing motivations (25.1%) had substantially greater explanatory power than demographic variables (8.1%). Account owners exhibited strong churn tendencies, while sharing beneficiaries sought workarounds. This study extends platform policy research by multidimensionally predicting user behaviors through explainable AI techniques, providing practical implications for OTT service policy formulation.

본 연구는 넷플릭스의 계정 공유 제한 강화 정책에 대한 이용자의 대응 행동을 예측하기 위해 기계학습 기반 다중 분류 모델을 구축하였다. 한국언론진흥재단의 설문 자료(n=681)를 활용하여 이용자 행동을 혼자 이용, 추가 요금 지불, 공유 중단, 편법 모색, 이탈의 5개 범주로 분류하고, 6가지 알고리즘을 비교한 결과 Random Forest가 정확도 0.664, Macro F1-score 0.602로 가장 우수한 성능을 보였으며, 이탈(89%)과 편법 모색(83%) 그룹을 높은 민감도로 탐지하였다. 순열 중요도(PI, Permutation Importance) 및 SHAP 분석 결과, 구독 구조(32.6%)와 공유 동기(25.1%)가 인구통계학적 변수(8.1%)보다 훨씬 큰 설명력을 보였다. 계정 소유자는 이탈 성향이, 공유 수혜자는 편법 모색 성향이 나타났다. 본 연구는 설명 가능한 AI 기법을 통해 이용자 행동을 다차원적으로 예측함으로써 OTT 서비스의 정책 수립에 실질적 시사점을 제공한다.

Keywords

References

  1. 양정애, "넷플릭스의 계정공유 제한 강화 정책에 대한 이용자 인식", 미디어 이슈, 제9권, 제2호, 2023, 한국언론진흥재단.
  2. Bhattacharyya, S. S., S. Goswami, R. Mehta, and B. Nayak, "Examining the factors influencing adoption of over the top (OTT) services among Indian consumers", Journal of Science and Technology Policy Management, Vol.13, No.3, 2022, pp. 652-682. https://doi.org/10.1108/JSTPM-09-2020-0135
  3. Bonini, T. and E. Treré, Algorithms of resistance: The everyday fight against platform power, MIT Press, Cambridge, MA, 2024
  4. Cimino, A., I. M. Coniglio, V. Corvello, F. Longo, J. K. Sagawa, and V. Solina, "Exploring small farmers behavioral intention to adopt digital platforms for sustainable and successful agricultural ecosystems", Technological Forecasting and Social Change, Vol.209, 2024, 123436.
  5. CNN, "Netflix cracked down on password sharing. The result? Millions of new subscribers", 2024, Available at https://edition.cnn.com/2024/04/18/business/netflix-earnings-first-quarter.
  6. Coussement, K., S. Lessmann, and G. Verstraeten, "A comparative analysis of data preparation algorithms for customer churn prediction: A case study in the telecommunication industry", Decision Support Systems, Vol.95, 2017, pp. 27-36. https://doi.org/10.1016/j.dss.2016.11.007
  7. Griggio, C. F., M. Nouwens, and C. N. Klokmose, "Caught in the network: the impact of WhatsApp's 2021 privacy policy update on users' messaging app ecosystems", Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, 2022, pp. 1-23.
  8. Hair, J. F., W. C. Black, B. J. Babin, R. E. Anderson, and R. L. Tatham, Multivariate Data Analysis, 2019.
  9. Hirschman, A. O., Exit, voice, and loyalty: Responses to decline in firms, organizations, and states, Harvard University Press, Cambridge, MA, 1972.
  10. Kim, Y., B. Oyunbold, and T. Roh, "Capturing OTT users in an emerging market: Insights on quality of OTT service and behavioral intentions through extended technology acceptance model", Journal of Retailing and Consumer Services, Vol.81, 2024, 103953.
  11. Lee, J., and Y. Jung, "Password-sharing on SVOD platforms: An examination through the lens of piracy neutralization", International Journal of Human-Computer Interaction, Vol.41, No.4, 2024.
  12. Lu, B., Z. Wang, and S. Zhang, "Platform-based mechanisms, institutional trust, and continuous use intention: The moderating role of perceived effectiveness of sharing economy institutional mechanisms", Information & Management, Vol.58, No.7, 2021, 103504. https://doi.org/10.1016/j.im.2021.103504
  13. Manzoor, A., M. Atif Qureshi, E. Kidney, and L. Longo, "A review on machine learning methods for customer churn prediction and recommendations for business practitioners", IEEE Access, Vol.12, 2024, pp. 70434-70463.
  14. Panda, A. R., M. K. Mishra, D. Kalsi, K. J. Bhuyan, S. Saha, and K. J. Bhuyan, "Classification of customer churning based on OTT platform data", Proceedings of the 2024 International Conference on Emerging Systems and Intelligent Computing (ESIC), Bhubaneswar, India, 2024, pp. 673-678.
  15. Redondo, I. and D. Serrano, "Authorized and unauthorized consumption of SVOD content: Modeling determinants of demand and measuring effects of enforcing access control", Journal of Theoretical and Applied Electronic Commerce Research, Vol.19, No.1, 2024, pp. 446-470. https://doi.org/10.3390/jtaer19010025
  16. Sailaja, Y., K. S. Reddy, M. A. Kalam, and T. Raviteja, "Customer churn prediction on OTT platforms", SSRN, 2025, Available at https://doi.org/10.2139/ssrn.5748682.
  17. Shin, S. and J. Park, "Factors affecting users' satisfaction and dissatisfaction of OTT services in South Korea", Telecommunications Policy, Vol.45, No.9, 2021, p. 102203. https://doi.org/10.1016/j.telpol.2021.102203
  18. Sperling, N., "Netflix starts to crack down on password sharing", International New York Times, May 2023.
  19. Sulaiman, D. Y. and V. U. Tjhin, "Continuance intention to subscribe to a video-on-demand service: A study of Netflix users in Indonesia", Journal of Theoretical and Applied Information Technology, Vol.101, No.5, 2023, pp.1819-1844.
  20. Van den Poel, D. and B. Lariviere, "Customer attrition analysis for financial services using proportional hazard models", European Journal of Operational Research, Vol.157, No.1, 2004, pp. 196-217. https://doi.org/10.1016/S0377-2217(03)00069-9
  21. Vo, N. N. Y., S. Liu, X. Li, and G. Xu, "Leveraging unstructured call log data for customer churn prediction", Knowledge-Based Systems, Vol.212, 2021, p. 106586. https://doi.org/10.1016/j.knosys.2020.106586
  22. Yoon, H. and H. K. Kim, "Why Do Consumers Continue to Use OTT Services?", Electronic Commerce Research and Applications, Vol.60, 2023, 101285.
  23. Zhang, W. and C. Challis, "Towards addressing unauthorized sharing of subscriptions", Applied Intelligence, Vol.52, No.15, 2022, pp. 17090-17102. https://doi.org/10.1007/s10489-021-02812-6
  24. Zhao, J., C. D. Lee, G. Chen, and J. Zhang, "Research on the prediction application of multiple classification datasets based on random forest model", Proceedings of the 2024 IEEE 6th International Conference on Power, Intelligent Computing and Systems (ICPICS), Chengdu, China, July 2024, pp. 1-6.