Skip to main content
SpringerLink
Log in

Online Experimentation for Information Retrieval

  • Chapter
  • First Online:
Information Retrieval (RuSSIR 2014)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 505))

Included in the following conference series:

Abstract

Online experimentation for information retrieval (IR) focuses on insights that can be gained from user interactions with IR systems, such as web search engines. The most common form of online experimentation, A/B testing, is widely used in practice, and has helped sustain continuous improvement of the current generation of these systems.

As online experimentation is taking a more and more central role in IR research and practice, new techniques are being developed to address, e.g., questions regarding the scale and fidelity of experiments in online settings. This paper gives an overview of the currently available tools. This includes techniques that are already in wide use, such as A/B testing and interleaved comparisons, as well as techniques that have been developed more recently, such as bandit approaches for online learning to rank.

This paper summarizes and connects the wide range of techniques and insights that have been developed in this field to date. It concludes with an outlook on open questions and directions for ongoing and future research.

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

Access this chapter

Log in via an institution

Institutional subscriptions

Notes

  1. 1.

    The terminology comes from the area of reinforcement learning, a type of machine learning in which an intelligent agent (e.g., an interactive IR system) learns from interactions with its environment (e.g., users) by trying out actions and observing rewards. This is a natural model for learning in interactive IR, and is discussed in more detail in Sect. 6.

  2. 2.

    A policy defines a distribution over system actions, often conditioned on additional information, such as the history of previous interactions, or information about context, such as a query posed by the user.

References

  1. Agrawal, S., Goyal, N.: Analysis of thompson sampling for the multi-armed bandit problem. In: COLT 2012 (2012)

    Google Scholar 

  2. Ailon, N., Karnin, Z., Joachims, T.: Reducing dueling bandits to cardinal bandits. In: ICML 2014 (2014)

    Google Scholar 

  3. Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47(2–3), 235–256 (2002)

    Article  MATH  Google Scholar 

  4. Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.E.: The nonstochastic multiarmed bandit problem. SIAM J. Comput. 32(1), 48–77 (2002)

    Article  MathSciNet  MATH  Google Scholar 

  5. Babbie, E.R.: The Practice of Social Research, 13th edn. Cengage Learning, Boston (2012)

    Google Scholar 

  6. Balog, K., Kelly, L., Schuth, A.: Head first: Living labs for ad-hoc search evaluation. In: CIKM 2014 (2014)

    Google Scholar 

  7. Bendersky, M., Garcia-Pueyo, L., Harmsen, J., Josifovski, V., Lepikhin, D.: Up next: Retrieval methods for large scale related video suggestion. In: KDD 2014 (2014)

    Google Scholar 

  8. Bottou, L., Chickering, J., Portugaly, E., Ray, D., Simard, P., Snelson, E.: Counterfactual reasoning and learning systems: The example of computational advertising. J. Mach. Learn. Res. 14(1), 3207–3260 (2013)

    MathSciNet  MATH  Google Scholar 

  9. Bubeck, S., Cesa-Bianchi, N.: Regret analysis of stochastic and nonstochastic multi-armed bandit problems. Found. Trends Mach. Learn. 5(1), 1–122 (2012)

    Article  MATH  Google Scholar 

  10. Busa-Fekete, R., Hüllermeier, E.: A survey of preference-based online learning with bandit algorithms. In: Auer, P., Clark, A., Zeugmann, T., Zilles, S. (eds.) ALT 2014. LNCS, vol. 8776, pp. 18–39. Springer, Heidelberg (2014)

    Chapter  MATH  Google Scholar 

  11. Carterette, B.: Statistical significance testing in information retrieval: Theory and practice. In: ICTIR 2013 (2013)

    Google Scholar 

  12. Chakraborty, S., Radlinski, F., Shokouhi, M., Baecke, P.: On correlation of absence time and search effectiveness. In: SIGIR 2014, pp. 1163–1166 (2014)

    Google Scholar 

  13. Chapelle, O., Li, L.: An empirical evaluation of thompson sampling. In: NIPS 2011, pp. 2249–2257 (2011)

    Google Scholar 

  14. Chapelle, O., Zhang, Y.: A dynamic bayesian network click model for web search ranking. In: WWW 2009, pp. 1–10 (2009)

    Google Scholar 

  15. Chapelle, O., Joachims, T., Radlinski, F., Yue, Y.: Large-scale validation and analysis of interleaved search evaluation. ACM Trans. Inf. Syst. 30(1), 6:1–6:41 (2012)

    Article  Google Scholar 

  16. Chuklin, A., Schuth, A., Hofmann, K., Serdyukov, P., de Rijke, M.: Evaluating aggregated search using interleaving. In: CIKM 2013 (2013)

    Google Scholar 

  17. Chuklin, A., Schuth, A., Zhou, K., de Rijke, M.: A comparative analysis of interleaving methods for aggregated search. ACM Trans. Inf. Syst. (2014)

    Google Scholar 

  18. Craswell, N., Zoeter, O., Taylor, M., Ramsey, B.: An experimental comparison of click position-bias models. In: WSDM 2008, pp. 87–94 (2008)

    Google Scholar 

  19. Deng, A., Xu, Y., Kohavi, R., Walker, T.: Improving the sensitivity of online controlled experiments by utilizing pre-experiment data. In: WSDM 2013, pp. 123–132 (2013)

    Google Scholar 

  20. Diaz, F.: Adaptation of offline vertical selection predictions in the presence of user feedback. In: SIGIR 2009, pp. 323–330 (2009)

    Google Scholar 

  21. Dupret, G., Lalmas, M.: Absence time and user engagement. In: WSDM 2013, p. 173. ACM Press, New York, February 2013

    Google Scholar 

  22. Granka, L.A., Joachims, T., Gay, G.: Eye-tracking analysis of user behavior in www search. In: SIGIR 2004, pp. 478–479 (2004)

    Google Scholar 

  23. Guan, Z., Cutrell, E.: An eye tracking study of the effect of target rank on web search. In: CHI 2007, pp. 417–420 (2007)

    Google Scholar 

  24. Hassan, A., White, R.W.: Personalized models of search satisfaction. In: CIKM 2013, pp. 2009–2018 (2013)

    Google Scholar 

  25. Hofmann, K., Whiteson, S., de Rijke, M.: Balancing exploration and exploitation in learning to rank online. In: Clough, P., Foley, C., Gurrin, C., Jones, G.J.F., Kraaij, W., Lee, H., Mudoch, V. (eds.) ECIR 2011. LNCS, vol. 6611, pp. 251–263. Springer, Heidelberg (2011)

    Chapter  Google Scholar 

  26. Hofmann, K., Whiteson, S., de Rijke, M.: A probabilistic method for inferring preferences from clicks. In: CIKM 2011, pp. 249–258 (2011)

    Google Scholar 

  27. Hofmann, K., Behr, F., Radlinski, F.: On caption bias in interleaving experiments. In: CIKM 2012, pp. 115–124. ACM Press (2012)

    Google Scholar 

  28. Hofmann, K., Whiteson, S., de Rijke, M.: Estimating interleaved comparison outcomes from historical click data. In: CIKM 2012, pp. 1779–1783 (2012)

    Google Scholar 

  29. Hofmann, K., Whiteson, S., de Rijke, M.: Balancing exploration and exploitation in listwise and pairwise online learning to rank for information retrieval. Inf. Retrieval J. 16(1), 63–90 (2013)

    Article  Google Scholar 

  30. Hofmann, K., Whiteson, S., de Rijke, M.: Fidelity, soundness, and efficiency of interleaved comparison methods. ACM Trans. Inf. Syst. 31(4), 1–43 (2013)

    Article  Google Scholar 

  31. Hofmann, K., Mitra, B., Radlinski, F., Shokouhi, M.: An eye-tracking study of user interactions with query auto completion. In: CIKM 2014 (2014)

    Google Scholar 

  32. Jie, L., Lamkhede, S., Sapra, R., Hsu, E., Song, H., Chang, Y.: A unified search federation system based on online user feedback. In: KDD 2013, pp. 1195–1203 (2013)

    Google Scholar 

  33. Jin, X., Sloan, M., Wang, J.: Interactive exploratory search for multi page search results. In: WWW 2013, pp. 655–666 (2013)

    Google Scholar 

  34. Joachims, T.: Optimizing search engines using clickthrough data. In: KDD 2002, pp. 133–142 (2002)

    Google Scholar 

  35. Joachims, T., Granka, L., Pan, B., Hembrooke, H., Radlinski, F., Gay, G.: Evaluating the accuracy of implicit feedback from clicks and query reformulations in web search. ACM Trans. Inf. Syst. 25(2), 1–26 (2007)

    Article  Google Scholar 

  36. Kaufmann, E., Korda, N., Munos, R.: Thompson sampling: an asymptotically optimal finite-time analysis. In: Bshouty, N.H., Stoltz, G., Vayatis, N., Zeugmann, T. (eds.) ALT 2012. LNCS, vol. 7568, pp. 199–213. Springer, Heidelberg (2012)

    Chapter  Google Scholar 

  37. Kazai, G., Kamps, J., Koolen, M., Milic-Frayling, N.: Crowdsourcing for book search evaluation: Impact of hit design on comparative system ranking. In: SIGIR 2011, pp. 205–214 (2011)

    Google Scholar 

  38. Kelly, D.: Methods for evaluating interactive information retrieval systems with users. Found. Trends Inf. Retrieval 3(1–2), 1–224 (2009)

    Google Scholar 

  39. Kelly, D., Teevan, J.: Implicit feedback for inferring user preference: a bibliography. SIGIR Forum 37(2), 18–28 (2003)

    Article  Google Scholar 

  40. Kelly, D., Gyllstrom, K., Bailey, E.W.: A comparison of query and term suggestion features for interactive searching. In: SIGIR 2009, p. 371. ACM Press, New York, July 2009

    Google Scholar 

  41. Kim, Y., Hassan, A., White, R.W., Zitouni, I.: Modeling dwell time to predict click-level satisfaction. In: WSDM 2014, pp. 193–202. ACM, New York (2014)

    Google Scholar 

  42. Kleinberg, R., Slivkins, A., Upfal, E.: Multi-armed bandits in metric spaces. In: STOC 2008. ACM Press (2008)

    Google Scholar 

  43. Kohavi, R., Longbotham, R., Sommerfield, D., Henne, R.M.: Controlled experiments on the web: survey and practical guide. Data Min. Knowl. Disc. 18(1), 140–181 (2009)

    Article  MathSciNet  Google Scholar 

  44. Kohavi, R., Deng, A., Frasca, B., Longbotham, R., Walker, T., Xu, Y.: Trustworthy online controlled experiments: Five puzzling outcomes explained. In: KDD 2012, pp. 786–794. ACM, New York (2012)

    Google Scholar 

  45. Kohavi, R., Deng, A., Frasca, B., Walker, T., Xu, Y., Pohlmann, N.: Online controlled experiments at large scale. In: KDD 2013, pp. 1168–1176. ACM, New York (2013)

    Google Scholar 

  46. Kohli, P., Salek, M., Stoddard, G.: A fast bandit algorithm for recommendation to users with heterogenous tastes. In: AAAI 2013 (2013)

    Google Scholar 

  47. Langford, J., Zhang, T.: The epoch-greedy algorithm for multi-armed bandits with side information. In: NIPS 2008, pp. 817–824 (2008)

    Google Scholar 

  48. Langford, J., Strehl, A., Wortman, J.: Exploration scavenging. In: ICML 2008, pp. 528–535 (2008)

    Google Scholar 

  49. Li, L., Chu, W., Langford, J., Schapire, R.E.: A contextual-bandit approach to personalized news article recommendation. In: WWW 2010, pp. 661–670 (2010)

    Google Scholar 

  50. Li, L., Chu, W., Langford, J., Wang, X.: Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms. In: WSDM 2011, pp. 297–306 (2011)

    Google Scholar 

  51. Li, L., Chen, S., Kleban, J., Gupta, A.: Couterfactual estimation and optimization of click metrics for search engines (2014). arXiv preprint arXiv:1403.1891

  52. Luo, J., Zhang, S., Yang, H.: Win-win search: Dual-agent stochastic game in session search. In: SIGIR 2014, pp. 587–596. ACM (2014)

    Google Scholar 

  53. Mahajan, D.K., Rastogi, R., Tiwari, C., Mitra, A.: LogUCB: An explore-exploit algorithm for comments recommendation. In: CIKM 2012, pp. 6–15 (2012)

    Google Scholar 

  54. Pearl, J.: Causality: Models, Reasoning and Inference, vol. 29. Cambridge University Press, Cambridge (2000)

    MATH  Google Scholar 

  55. Pearl, J.: An introduction to causal inference. Int. J. Biostatistics 6(2) (2010)

    Google Scholar 

  56. Precup, D., Sutton, R.S., Singh, S.P.: Eligibility traces for off-policy policy evaluation. In: ICML 2000, pp. 759–766 (2000)

    Google Scholar 

  57. Radlinski, F., Craswell, N.: Comparing the sensitivity of information retrieval metrics. In: SIGIR 2010, pp. 667–674 (2010)

    Google Scholar 

  58. Radlinski, F., Craswell, N.: Optimized interleaving for online retrieval evaluation. In: WSDM 2013 (2013)

    Google Scholar 

  59. Radlinski, F., Joachims, T.: Minimally invasive randomization for collecting unbiased preferences from clickthrough logs. In: AAAI 2006, p. 1406 (2006)

    Google Scholar 

  60. Radlinski, F., Kleinberg, R., Joachims, T.: Learning diverse rankings with multi-armed bandits. In: ICML 2008, pp. 784–791. ACM (2008)

    Google Scholar 

  61. Radlinski, F., Kurup, M., Joachims, T.: How does clickthrough data reflect retrieval quality?. In: CIKM 2008, pp. 43–52 (2008)

    Google Scholar 

  62. Russo, D., Roy, B.V.: An information-theoretic analysis of thompson sampling. CoRR, abs/1403.5341 (2014). URL http://arxiv.org/abs/1403.5341

  63. Sanderson, M.: Test collection based evaluation of information retrieval systems. Found. Trends Inf. Retrieval 4(4), 247–375 (2010)

    Article  MATH  Google Scholar 

  64. Scholer, F., Shokouhi, M., Billerbeck, B., Turpin, A.: Using clicks as implicit judgments: expectations versus observations. In: Macdonald, C., Ounis, I., Plachouras, V., Ruthven, I., White, R.W. (eds.) ECIR 2008. LNCS, vol. 4956, pp. 28–39. Springer, Heidelberg (2008)

    Chapter  Google Scholar 

  65. Schuth, A., Hofmann, K., Whiteson, S., de Rijke, M.: Lerot: an online learning to rank framework. In: LivingLab 2013, pP. 23–26. ACM (2013)

    Google Scholar 

  66. Schuth, A., Sietsma, F., Whiteson, S., de Rijke, M.: Optimizing base rankers using clicks. In: de Rijke, M., Kenter, T., de Vries, A.P., Zhai, C.X., de Jong, F., Radinsky, K., Hofmann, K. (eds.) ECIR 2014. LNCS, vol. 8416, pp. 75–87. Springer, Heidelberg (2014)

    Chapter  Google Scholar 

  67. Schuth, A., Sietsma, F., Whiteson, S., Lefortier, D., de Rijke, M.: Multileaved comparisons for fast online evaluation. In: CIKM 2014 (2014)

    Google Scholar 

  68. Slivkins, A., Radlinski, F., Gollapudi, S.: Ranked bandits in metric spaces: learning diverse rankings over large document collections. J. Mach. Learn. Res. 14(1), 399–436 (2013)

    MathSciNet  MATH  Google Scholar 

  69. Song, Y., Shi, X., Fu, X.: Evaluating and predicting user engagement change with degraded search relevance. In: WWW 2013, pp. 1213–1224 (2013)

    Google Scholar 

  70. Streeter, M., Golovin, D., Krause, A.: Online learning of assignments. In: NIPS 2009, pp. 1794–1802 (2009)

    Google Scholar 

  71. Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning. MIT Press, Cambridge (1998)

    Book  MATH  Google Scholar 

  72. Tang, D., Agarwal, A., O’Brien, D., Meyer, M.: Overlapping experiment infrastructure: More, better, faster experimentation. In: KDD 2010, pp. 17–26 (2010)

    Google Scholar 

  73. Tang, L., Rosales, R., Singh, A., Agarwal, D.: Automatic ad format selection via contextual bandits. In: CIKM 2013, pp. 1587–1594 (2013)

    Google Scholar 

  74. Valko, M., Carpentier, A., Munos, R.: Stochastic simultaneous optimistic optimization. In: ICML 2013, pp. 19–27 (2013)

    Google Scholar 

  75. Voorhees, E.M., Harman, D.K.: TREC: Experiment and Evaluation in Information Retrieval. Digital Libraries and Electronic Publishing. MIT Press, Cambridge (2005)

    Google Scholar 

  76. Wang, K., Walker, T., Zheng, Z.: PSkip: estimating relevance ranking quality from web search clickthrough data. In: KDD 2009, pp. 1355–1364 (2009)

    Google Scholar 

  77. Watkins, C.J.C.H.: Learning from delayed rewards. Ph.D. thesis, University of Cambridge (1989)

    Google Scholar 

  78. Yue, Y., Guestrin, C.: Linear submodular bandits and their application to diversified retrieval. In: Shawe-Taylor, J., Zemel, R., Bartlett, P., Pereira, F., Weinberger, K. (eds.) NIPS 2011, pp. 2483–2491 (2011)

    Google Scholar 

  79. Yue, Y., Joachims, T.: Interactively optimizing information retrieval systems as a dueling bandits problem. In: ICML 2009, pp. 1201–1208 (2009)

    Google Scholar 

  80. Yue, Y., Joachims, T.: Beat the mean bandit. In: ICML 2011 (2011)

    Google Scholar 

  81. Yue, Y., Broder, J., Kleinberg, R., Joachims, T.: The K-armed dueling bandits problem. In: COLT 2009 (2009)

    Google Scholar 

  82. Yue, Y., Patel, R., Roehrig, H.: Beyond position bias: examining result attractiveness as a source of presentation bias in clickthrough data. In: WWW 2010, pp. 1011–1018 (2010)

    Google Scholar 

  83. Yue, Y., Broder, J., Kleinberg, R., Joachims, T.: The K-armed dueling bandits problem. J. Comput. Syst. Sci. 78(5), 1538–1556 (2012)

    Article  MathSciNet  MATH  Google Scholar 

  84. Zoghi, M., Whiteson, S.A., de Rijke, M., Munos, R.: Relative confidence sampling for efficient on-line ranker evaluation. In: WSDM 2014, pp. 73–82 (2014)

    Google Scholar 

  85. Zoghi, M., Whiteson, S.A., Munos, R., de Rijke, M.: Relative upper confidence bound for the K-armed dueling bandit problem. In: ICML 2014 (2014)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Microsoft Research, Cambridge, UK

    Katja Hofmann

Authors
  1. Katja Hofmann
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Katja Hofmann .

Editor information

Editors and Affiliations

  1. Ural Federal University, Yekaterinburg, Russia

    Pavel Braslavski

  2. National Research University Higher School of Economics, Nizhniy Novgorod, Russia

    Nikolay Karpov

  3. Intelligent Systems Laboratory, University of Amsterdam, Amsterdam, The Netherlands

    Marcel Worring

  4. Barcelona Media Research Foundation, Barcelona, Spain

    Yana Volkovich

  5. National Research University Higher School of Economics, Moscow, Russia

    Dmitry I. Ignatov

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this chapter

Cite this chapter

Hofmann, K. (2015). Online Experimentation for Information Retrieval. In: Braslavski, P., Karpov, N., Worring, M., Volkovich, Y., Ignatov, D.I. (eds) Information Retrieval. RuSSIR 2014. Communications in Computer and Information Science, vol 505. Springer, Cham. https://doi.org/10.1007/978-3-319-25485-2_2

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-25485-2_2

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-25484-5

  • Online ISBN: 978-3-319-25485-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation