Skip to main content
Log in

Matrix- and Tensor Factorization for Game Content Recommendation

  • Technical Contribution
  • Published:
KI - Künstliche Intelligenz Aims and scope Submit manuscript

Abstract

Commercial success of modern freemium games hinges on player satisfaction and retention. This calls for the customization of game content or game mechanics in order to keep players engaged. However, whereas game content is already frequently generated using procedural content generation, methods that can reliably assess what kind of content suits a player’s skills or preferences are still few and far between. Addressing this challenge, we propose novel recommender systems based on latent factor models that allow for recommending quests in a single player role-playing game. In particular, we introduce a tensor factorization algorithm to decompose collections of bipartite matrices which represent how players’ interests and behaviors change over time. Extensive online bucket type tests during the ongoing operation of a commercial game reveal that our system is able to recommend more engaging quests and to retain more players than previous handcrafted or collaborative filtering approaches.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Notes

  1. The game is an HTML5 application hosted on Toggo: http://www.toggo.de/serien/trolljaeger/index-4310.htm

  2. The QR decomposition of an arbitrary matrix \(\varvec{M}\) is to compute \(\varvec{Q},\varvec{R} \leftarrow QR\bigl ( \varvec{M} \bigr )\), where \(\varvec{Q}\) is orthogonal and \(\varvec{R}\) is upper triangular.

References

  1. Bader B, Harshman R, Kolda T (2007) Temporal analysis of semantic graphs using ASALSAN. In: Proceedings of the IEEE international conference on data mining (ICDM), pp 33–42

  2. Chen J (2007) Flow in games (and everything else). Commun ACM 50(4):31–34

    Article  Google Scholar 

  3. Cremonesi P, Koren Y, Turrin R (2010) Performance of recommender algorithms on top-N recommendation tasks. In: Proceedings of the ACM conference series on recommender systems (RECSYS), pp 39–46

  4. Drachen A, Thurau C, Togelius J, Yannakakis GN, Bauckhage C (2013) Game data mining. In: Seif El-Nasr M, Drachen A, Canossa A (eds) Game analytics—maximizing the value of player data. Springer, Berlin, pp 205–253

    Google Scholar 

  5. Furnas GW, Deerwester S, Dumais ST, Landauer TK, Harshman RA, Streeter LA, Lochbaum KE (1988) Information retrieval using a singular value decomposition model of latent semantic structure. In: Proceedings of ACM SIGIR conference on research & development in information retrieval (SIGIR), pp 465–480

  6. Hadiji F, Sifa R, Drachen A, Thurau C, Kersting K, Bauckhage C (2014) Predicting player churn in the wild. In: Proceedings of the IEEE conference on computational intelligence and games (CIG)

  7. Harshman RA (1978) Models for analysis of asymmetrical relationships among N objects or stimuli. In: Proceedings of joint meeting of the psychometric society and the society for mathematical psychology, McMaster University, Hamilton, Ontario

  8. Hofmann T (2004) Latent semantic models for collaborative filtering. ACM Trans Inf Syst 22(1):89–115

    Article  Google Scholar 

  9. Kolda TG, Bader BW (2009) Tensor decompositions and applications. SIAM Rev 51(3):455–500

    Article  MathSciNet  Google Scholar 

  10. Kroonenberg Pieter M (1994) The TUCKALS line: a suite of programs for three-way data analysis. Comput Stat Data Anal 18(1):73–96

    Article  Google Scholar 

  11. Kunegis J, Schmidt S, Albayrak S, Bauckhage C, Mehlitz M (2008) Modeling collaborative similarity with the signed resistance distance kernel. In: Proceedings of the European conference on artificial intelligence (ECAI), pp 261–265

  12. Leskovec J, Rajaraman A, Ullman JD (2014) Mining of massive datasets, chapter 9. Cambridge University Press, Cambridge

    Book  Google Scholar 

  13. Meidl M, Lytinen S, Raison K (2014) Using game reviews to recommend games. In: Proceedings of the AAAI conference on artififical intelligence for interactive digital entertainment (AIIDE), pp 24–29

  14. Runge J, Gao P, Garcin F, Faltings B (2014) Churn prediction for high-value players in casual social games. In: Proceedings of the IEEE conference on computational intelligence and games (CIG)

  15. Ryan JO, Kaltman E, Hong T, Mateas M, Wardrip-Fruin N (2015) People tend to like related games. In: Proceedings of the conference on foundations of digital games (FDG)

  16. Ryan JO, Kaltman E, Mateas M, Wardrip-Fruin N (2015) What we talk about when we talk about games: bottom-up game studies using natural language processing. In: Proceedings of the conference on foundations of digital games (FDG)

  17. Saas A, Guitart A, Perianez A (2016) Discovering playing patterns: time series clustering of free-to-play game data. In: Proceedings of the IEEE conference on computational intelligence and games (CIG)

  18. Sharma M, Ontañón S, Mehta M, Ram A (2010) Drama management and player modeling for interactive fiction games. Comput Intell 26(2):183–211

    Article  MathSciNet  Google Scholar 

  19. Sifa R (2019) Matrix and tensor factorization for profiling player behavior. LeanPub, Victoria

    Google Scholar 

  20. Sifa R, Bauckhage C, Drachen A (2014) Archetypal game recommender systems. In: Proceedings of Learning, Knowledge, Adaptation (LWA), pp 45–56

  21. Sifa R, Hadiji F, Runge J, Drachen A, Kersting K, Bauckhage C (2015) Predicting purchase decisions in mobile free-to-play games. In: Proceedings of the AAAI conference on artififical intelligence for interactive digital entertainment (AIIDE)

  22. Sifa R, Ojeda C, Bauckhage C (2015) User churn migration analysis with DEDICOM. In: Proceedings of the ACM conference series on recommender systems (RECSYS), pp 321–324

  23. Sifa R, Pawlakos E, Zhai K, Haran S, Jha R, Klabjan D, Drachen A (2018) Controlling the crucible: a novel PvP recommender systems framework for destiny. In: Proceedings of the ACM Australasian computer science week multiconference (ACSW)

  24. Sifa R, Srikanth S, Drachen A, Ojeda C, Bauckhage C (2016) Predicting retention in sandbox games with tensor factorization-based representation learning. In: Proceedings of the IEEE conference on computational intelligence and games (CIG)

  25. Smith B, Linden G (2017) Two decades of recommender systems at Amazon.com. IEEE Internet Comput 21(3):12–18

    Article  Google Scholar 

  26. Ten Berge JMF (1983) A generalization of Kristof’s theorem on the trace of certain matrix products. Psychometrika 48(4):519–523

    Article  MathSciNet  Google Scholar 

  27. Tucker LR (1966) Some mathematical notes on three-mode factor analysis. Psychometrika 31(3):279–311

    Article  MathSciNet  Google Scholar 

  28. Viljanen M, Airola A, Heikkonen J, Pahikkala T (2018) Playtime measurement with survival analysis. IEEE Trans Games 10(2):128–138

    Article  Google Scholar 

  29. Weber B (2015) Building a recommendation system for EverQuest landmark’s marketplace. Presentation at GDC

  30. Xie H, Devlin S, Kudenko D, Cowling P (2015) Predicting player disengagement and first purchase with event-frequency based data representation. In: Proceedings of the IEEE conference on computational intelligence and games (CIG), pp 230–237

  31. Yanakakis GN (2012) Game AI revisited. In: Proceedings of the ACM Conference on computing frontiers (CF), pp 285–292

  32. Zook A, Lee-Urban S, Drinkwater MR, Riedl MO (2012) Skill-based mission generation: a data-driven temporal player modeling approach. In: Proceedings of ACM workshop on procedural content generation in games

Download references

Acknowledgements

We would like to thank the anonymous reviewers for their insightful comments. We would like to thank Flying Sheep Studios and the developers of Trolljäger: Abenteuer in den Trollhöhlen for creating the platform, providing us with access to their analytics suite, and supporting us with the evaluation process. Additionally, we would like to thank SRTL for supporting us to conduct this study. In parts, the work reported here was funded by the Fraunhofer Center for Machine Learning within the Fraunhofer Cluster of Excellence Cognitive Internet Technologies (CCIT).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Christian Bauckhage.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sifa, R., Yawar, R., Ramamurthy, R. et al. Matrix- and Tensor Factorization for Game Content Recommendation. Künstl Intell 34, 57–67 (2020). https://doi.org/10.1007/s13218-019-00620-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13218-019-00620-2

Keywords

Navigation