Using Multi-armed Bandit to Solve Cold-Start Problems in Recommender Systems at Telco

  • Hai Thanh Nguyen
  • Anders Kofod-Petersen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8891)


Recommending best-fit rate-plans for new users is a challenge for the Telco industry. Rate-plans differ from most traditional products in the way that a user normally only have one product at any given time. This, combined with no background knowledge on new users hinders traditional recommender systems. Many Telcos today use either trivial approaches, such as picking a random plan or the most common plan in use. The work presented here shows that these methods perform poorly. We propose a new approach based on the multi-armed bandit algorithms to automatically recommend rate-plans for new users. An experiment is conducted on two different real-world datasets from two brands of a major international Telco operator showing promising results.


multi-armed bandit cold-start recommender systems telecom rate-plan 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Park, S.T., Pennock, D., Madani, O., Good, N., DeCoste, D.: Naïve filterbots for robust cold-start recommendations. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 699–705 (2006)Google Scholar
  2. 2.
    Adomavicius, G., Tuzhilin, A.: Towards the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE Transactions on Knowledge and Data Engineering 17, 734–749 (2005)CrossRefGoogle Scholar
  3. 3.
    Massa, P., Bhattacharjee, B.: Using trust in recommender systems: An experimental analysis. In: Jensen, C., Poslad, S., Dimitrakos, T. (eds.) iTrust 2004. LNCS, vol. 2995, pp. 221–235. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  4. 4.
    Burke, R.: Hybrid recommender systems: Survey and experiments. user modeling and user-adapted interaction. User Modeling and User-Adapted Interaction 12, 331–370 (2002)CrossRefzbMATHGoogle Scholar
  5. 5.
    Lai, T.L., Robbins, H.: Asymptotically efficient adaptive allocation rules. Advances in Applied Mathematics 6, 4–22 (1985)CrossRefzbMATHMathSciNetGoogle Scholar
  6. 6.
    Katehakis, M., Veinott, J.A.: The multi-armed bandit problem: decomposition and computation. Mathematics of Operations Research 12, 262–268 (1987)CrossRefzbMATHMathSciNetGoogle Scholar
  7. 7.
    Auer, P., Cesa-Bainchi, M., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Machine Learning 47, 235–256 (2002)CrossRefzbMATHGoogle Scholar
  8. 8.
    Thomas, S., Wilson, J., Chaudhury, S.: Best-fit mobile recharge pack recommendation. In: National Conference on Communications (NCC), pp. 1–5 (2013)Google Scholar
  9. 9.
    Soonsiripanichkul, B., Tongtep, N., Theeramunkong, T.: Mobile package recommendation using classification with feature discretization and threshold-based ensemble technique. In: Proceedings of the International Conference on Information and Communication Technology for Embedded Systems, ICICTES 2014 (2014)Google Scholar
  10. 10.
    Lekakos, G., Giaglis, G.M.: A hybrid approach for improving predictive accuracy of collaborative filtering algorithms. User Modeling and User-Adapted Interaction 17, 5–40 (2007)CrossRefGoogle Scholar
  11. 11.
    Lam, X.N., Vu, T., Le, T.D., Duong, A.D.: Addressing cold-start problem in recommendation systems. In: Proceedings of the 2nd International Conference on Ubiquitous Information Management and Communication, pp. 208–211. ACM (2008)Google Scholar
  12. 12.
    Marlin, B.: Collaborative filtering: A machine learning perspective. Technical report, University of Toronto (2004)Google Scholar
  13. 13.
    Gao, F., Xing, C., Du, X., Wang, S.: Personalized service system based on hybrid filtering for digital library. Tsinghua Science & Technology 12, 1–8 (2007)CrossRefGoogle Scholar
  14. 14.
    Agarwal, D., Chen, B.C.: Regression-based latent factor models. In: KDD 2009: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM SIGKDD, pp. 19–28. ACM (2009)Google Scholar
  15. 15.
    Park, S.T., Chu, W.: Pairwise preference regression for cold-start recommendation. In: RecSys 2009: Proceedings of ACM conference on Recommender systems, pp. 21–28 (2009)Google Scholar
  16. 16.
    Zigoris, P., Zhang, Y.: Bayesian adaptive user profiling with explicit & implicit feedback. In: CIKM 2006: Proceedings of the 15th ACM International Conference on Information and Knowledge Management, pp. 397–404. ACM (2006)Google Scholar
  17. 17.
    Manavoglu, E., Pavlov, D., Giles, C.L.: Probabilistic user behavior models. In: ICDM 2003: Proceedings of Third IEEE International Conference on Data Mining (2003)Google Scholar
  18. 18.
    Xue, G.R., Han, J., Yu, Y., Yang, Q.: User language model for collaborative personalized search. ACM Transactions on Information Systems 27, 1–28 (2009)CrossRefGoogle Scholar
  19. 19.
    Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.E.: The nonstochastic multiarmed bandit problem. SIAM Journal on Computing 32, 48–77 (2002)CrossRefzbMATHMathSciNetGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Hai Thanh Nguyen
    • 1
  • Anders Kofod-Petersen
    • 1
    • 2
  1. 1.Telenor ResearchTrondheimNorway
  2. 2.Department of Computer and Information Science (IDI)Norwegian University of Science and Technology (NTNU)TrondheimNorway

Personalised recommendations