On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-$n$ Recommendation

• URL: http://arxiv.org/abs/2307.15053v3
• Date: Wed, 12 Jun 2024 16:01:45 GMT
• Title: On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-$n$ Recommendation
• Authors: Olivier Jeunen, Ivan Potapov, Aleksei Ustimenko,
• Abstract summary: Discounted Cumulative Gain (nDCG) is one such metric that has seen widespread adoption in empirical studies. We show that our unbiased DCG estimates strongly correlate with online reward, even when some of the metric's inherent assumptions are violated.
• Score: 12.036747050794135
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Approaches to recommendation are typically evaluated in one of two ways: (1) via a (simulated) online experiment, often seen as the gold standard, or (2) via some offline evaluation procedure, where the goal is to approximate the outcome of an online experiment. Several offline evaluation metrics have been adopted in the literature, inspired by ranking metrics prevalent in the field of Information Retrieval. (Normalised) Discounted Cumulative Gain (nDCG) is one such metric that has seen widespread adoption in empirical studies, and higher (n)DCG values have been used to present new methods as the state-of-the-art in top-$n$ recommendation for many years. Our work takes a critical look at this approach, and investigates when we can expect such metrics to approximate the gold standard outcome of an online experiment. We formally present the assumptions that are necessary to consider DCG an unbiased estimator of online reward and provide a derivation for this metric from first principles, highlighting where we deviate from its traditional uses in IR. Importantly, we show that normalising the metric renders it inconsistent, in that even when DCG is unbiased, ranking competing methods by their normalised DCG can invert their relative order. Through a correlation analysis between off- and on-line experiments conducted on a large-scale recommendation platform, we show that our unbiased DCG estimates strongly correlate with online reward, even when some of the metric's inherent assumptions are violated. This statement no longer holds for its normalised variant, suggesting that nDCG's practical utility may be limited.

Related papers

• Estimating Treatment Effects under Recommender Interference: A Structured Neural Networks Approach [13.208141830901845]
  We show that the standard difference-in-means estimator can lead to biased estimates due to recommender interference. We propose a "recommender choice model" that describes which item gets exposed from a pool containing both treated and control items. We show that the proposed estimator yields results comparable to the benchmark, whereas the standard difference-in-means estimator can exhibit significant bias and even produce reversed signs.
  arXiv  Detail & Related papers  (2024-06-20T14:53:26Z)
• $Δ\text{-}{\rm OPE}$: Off-Policy Estimation with Pairs of Policies [13.528097424046823]
  We introduce $Deltatext-rm OPE$ methods based on the widely used Inverse Propensity Scoring estimator. Simulated, offline, and online experiments show that our methods significantly improve performance for both evaluation and learning tasks.
  arXiv  Detail & Related papers  (2024-05-16T12:04:55Z)
• Optimal Baseline Corrections for Off-Policy Contextual Bandits [61.740094604552475]
  We aim to learn decision policies that optimize an unbiased offline estimate of an online reward metric. We propose a single framework built on their equivalence in learning scenarios. Our framework enables us to characterize the variance-optimal unbiased estimator and provide a closed-form solution for it.
  arXiv  Detail & Related papers  (2024-05-09T12:52:22Z)
• Policy Gradient with Active Importance Sampling [55.112959067035916]
  Policy gradient (PG) methods significantly benefit from IS, enabling the effective reuse of previously collected samples. However, IS is employed in RL as a passive tool for re-weighting historical samples. We look for the best behavioral policy from which to collect samples to reduce the policy gradient variance.
  arXiv  Detail & Related papers  (2024-05-09T09:08:09Z)
• Aligning GPTRec with Beyond-Accuracy Goals with Reinforcement Learning [67.71952251641545]
  GPTRec is an alternative to the Top-K model for item-by-item recommendations. We show that GPTRec offers a better tradeoff between accuracy and secondary metrics than classic greedy re-ranking techniques. Our experiments on two datasets show that GPTRec's Next-K generation approach offers a better tradeoff between accuracy and secondary metrics than classic greedy re-ranking techniques.
  arXiv  Detail & Related papers  (2024-03-07T19:47:48Z)
• Variance Reduction in Ratio Metrics for Efficient Online Experiments [12.036747050794135]
  We apply variance reduction techniques to ratio metrics on a large-scale short-video platform: ShareChat. Our results show that we can either improve A/B-test confidence in 77% of cases, or can retain the same level of confidence with 30% fewer data points.
  arXiv  Detail & Related papers  (2024-01-08T18:01:09Z)
• How Human is Human Evaluation? Improving the Gold Standard for NLG with Utility Theory [47.10283773005394]
  We propose a new evaluation protocol called $textitsystem-level probabilistic assessment$ (SPA) We find that according to SPA, annotators prefer larger GPT-3 variants to smaller ones -- as expected -- with all comparisons being statistically significant. In our experiments, we find that according to SPA, annotators prefer larger GPT-3 variants to smaller ones -- as expected -- with all comparisons being statistically significant.
  arXiv  Detail & Related papers  (2022-05-24T09:51:27Z)
• Learning to Estimate Without Bias [57.82628598276623]
  Gauss theorem states that the weighted least squares estimator is a linear minimum variance unbiased estimation (MVUE) in linear models. In this paper, we take a first step towards extending this result to non linear settings via deep learning with bias constraints. A second motivation to BCE is in applications where multiple estimates of the same unknown are averaged for improved performance.
  arXiv  Detail & Related papers  (2021-10-24T10:23:51Z)
• Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactions [18.90946044396516]
  Music streaming, video streaming, news recommendation, and e-commerce services often engage with content in a sequential manner. Providing and evaluating good sequences of recommendations is therefore a central problem for these services. We propose a new counterfactual estimator that allows for sequential interactions in the rewards with lower variance in anally unbiased manner.
  arXiv  Detail & Related papers  (2020-07-25T17:58:01Z)
• Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems [84.3996727203154]
  We show that a popular choice of contrastive loss is equivalent to reducing the exposure bias via inverse propensity weighting. We further improve upon CLRec and propose Multi-CLRec, for accurate multi-intention aware bias reduction. Our methods have been successfully deployed in Taobao, where at least four-month online A/B tests and offline analyses demonstrate its substantial improvements.
  arXiv  Detail & Related papers  (2020-05-20T08:15:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.