IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2002.08536.html
   My bibliography  Save this paper

Debiased Off-Policy Evaluation for Recommendation Systems

Author

Listed:
  • Yusuke Narita
  • Shota Yasui
  • Kohei Yata

Abstract

Efficient methods to evaluate new algorithms are critical for improving interactive bandit and reinforcement learning systems such as recommendation systems. A/B tests are reliable, but are time- and money-consuming, and entail a risk of failure. In this paper, we develop an alternative method, which predicts the performance of algorithms given historical data that may have been generated by a different algorithm. Our estimator has the property that its prediction converges in probability to the true performance of a counterfactual algorithm at a rate of $\sqrt{N}$, as the sample size $N$ increases. We also show a correct way to estimate the variance of our prediction, thus allowing the analyst to quantify the uncertainty in the prediction. These properties hold even when the analyst does not know which among a large number of potentially important state variables are actually important. We validate our method by a simulation experiment about reinforcement learning. We finally apply it to improve advertisement design by a major advertisement company. We find that our method produces smaller mean squared errors than state-of-the-art methods.

Suggested Citation

  • Yusuke Narita & Shota Yasui & Kohei Yata, 2020. "Debiased Off-Policy Evaluation for Recommendation Systems," Papers 2002.08536, arXiv.org, revised Aug 2021.
  • Handle: RePEc:arx:papers:2002.08536
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2002.08536
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Maria Dimakopoulou & Zhengyuan Zhou & Susan Athey & Guido Imbens, 2017. "Estimation Considerations in Contextual Bandits," Papers 1711.07077, arXiv.org, revised Dec 2018.
    2. Victor Chernozhukov & Juan Carlos Escanciano & Hidehiko Ichimura & Whitney K. Newey & James M. Robins, 2022. "Locally Robust Semiparametric Estimation," Econometrica, Econometric Society, vol. 90(4), pages 1501-1535, July.
    3. Yusuke Narita & Shota Yasui & Kohei Yata, 2018. "Efficient Counterfactual Learning from Bandit Feedback," Cowles Foundation Discussion Papers 2155, Cowles Foundation for Research in Economics, Yale University.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Kyle Colangelo & Ying-Ying Lee, 2019. "Double debiased machine learning nonparametric inference with continuous treatments," CeMMAP working papers CWP72/19, Centre for Microdata Methods and Practice, Institute for Fiscal Studies.
    2. Kyle Colangelo & Ying-Ying Lee, 2019. "Double debiased machine learning nonparametric inference with continuous treatments," CeMMAP working papers CWP54/19, Centre for Microdata Methods and Practice, Institute for Fiscal Studies.
    3. Victor Chernozhukov & Whitney K. Newey & Victor Quintas-Martinez & Vasilis Syrgkanis, 2021. "Automatic Debiased Machine Learning via Riesz Regression," Papers 2104.14737, arXiv.org, revised Mar 2024.
    4. Zhengyuan Zhou & Susan Athey & Stefan Wager, 2023. "Offline Multi-Action Policy Learning: Generalization and Optimization," Operations Research, INFORMS, vol. 71(1), pages 148-183, January.
    5. Maximilian Blesch & Philipp Eisenhauer, 2021. "Robust decision-making under risk and ambiguity," Papers 2104.12573, arXiv.org, revised Oct 2021.
    6. Stéphane Bonhomme & Martin Weidner, 2020. "Minimizing Sensitivity to Model Misspecification," CeMMAP working papers CWP37/20, Centre for Microdata Methods and Practice, Institute for Fiscal Studies.
    7. Michael Lechner, 2023. "Causal Machine Learning and its use for public policy," Swiss Journal of Economics and Statistics, Springer;Swiss Society of Economics and Statistics, vol. 159(1), pages 1-15, December.
    8. Stéphane Bonhomme & Martin Weidner, 2022. "Minimizing sensitivity to model misspecification," Quantitative Economics, Econometric Society, vol. 13(3), pages 907-954, July.
    9. Karun Adusumilli & Dita Eckardt, 2019. "Temporal-Difference estimation of dynamic discrete choice models," Papers 1912.09509, arXiv.org, revised Dec 2022.
    10. Thomas H. Jørgensen, 2023. "Sensitivity to Calibrated Parameters," The Review of Economics and Statistics, MIT Press, vol. 105(2), pages 474-481, March.
    11. Hidehiko Ichimura & Whitney K. Newey, 2022. "The influence function of semiparametric estimators," Quantitative Economics, Econometric Society, vol. 13(1), pages 29-61, January.
    12. Pereda-Fernández, Santiago, 2023. "Identification and estimation of triangular models with a binary treatment," Journal of Econometrics, Elsevier, vol. 234(2), pages 585-623.
    13. Ben Deaner, 2021. "Many Proxy Controls," Papers 2110.03973, arXiv.org.
    14. Semenova, Vira, 2023. "Debiased machine learning of set-identified linear models," Journal of Econometrics, Elsevier, vol. 235(2), pages 1725-1746.
    15. Victor Chernozhukov & Vira Semenova, 2018. "Simultaneous inference for Best Linear Predictor of the Conditional Average Treatment Effect and other structural functions," CeMMAP working papers CWP40/18, Centre for Microdata Methods and Practice, Institute for Fiscal Studies.
    16. Sokbae Lee & Ryo Okui & Yoon†Jae Whang, 2017. "Doubly robust uniform confidence band for the conditional average treatment effect function," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 32(7), pages 1207-1225, November.
    17. Victor Chernozhukov & Carlos Cinelli & Whitney Newey & Amit Sharma & Vasilis Syrgkanis, 2021. "Long Story Short: Omitted Variable Bias in Causal Machine Learning," Papers 2112.13398, arXiv.org, revised Nov 2023.
    18. Kline, Patrick & Walters, Christopher, 2019. "Audits as Evidence: Experiments, Ensembles, and Enforcement," Institute for Research on Labor and Employment, Working Paper Series qt3z72m9kn, Institute of Industrial Relations, UC Berkeley.
    19. Kai Feng & Han Hong, 2024. "Statistical Inference of Optimal Allocations I: Regularities and their Implications," Papers 2403.18248, arXiv.org, revised Apr 2024.
    20. Vasilis Syrgkanis & Ruohan Zhan, 2023. "Post-Episodic Reinforcement Learning Inference," Papers 2302.08854, arXiv.org, revised Jul 2023.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2002.08536. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.