EconBase
← All papers

Tackling Interference Induced by Data Training Loops in A/B Tests: A Weighted Training Approach

Nian Si

arXiv 26 Oct 2023 · Statistics — Methodology · 2 citations (OpenAlex)

arXiv:2310.17496 · PDF · DOI · OpenAlex · Extracted main text

Abstract

In modern recommendation systems, the standard pipeline involves training machine learning models on historical data to predict user behaviors and improve recommendations continuously. However, these data training loops can introduce interference in A/B tests, where data generated by control and treatment algorithms, potentially with different distributions, are combined. To address these challenges, we introduce a novel approach called weighted training. This approach entails training a model to predict the probability of each data point appearing in either the treatment or control data and subsequently applying weighted losses during model training. We demonstrate that this approach achieves the least variance among all estimators that do not cause shifts in the training distributions. Through simulation studies, we demonstrate the lower bias and variance of our approach compared to other methods.

Citation extraction

65
references
78
in-text mentions
65
distinct cited
1
self-citations
7,744
main-text words

appendix boundary found by appendix_command · 85% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1David Holtz, Jennifer Brennan, and Jean Pouget-Abadie (2023) A study of" symbiosis bias" in a/b tests of recommendation algorithms1.00054100%
2Allison JB Chaney, Brandon M Stewart, and Barbara E Engelhardt (2018) How algorithmic confounding in recommendation systems increases homogeneity and decreases utility0.64422100%
3Guido W Imbens and Donald B Rubin (2015) Causal inference in statistics, social, and biomedical sciences0.64422100%
4Amir H Jadidinejad, Craig Macdonald, and Iadh Ounis (2020) Using exploration to alleviate closed loop effects in recommender systems0.64422100%
5Diederik P Kingma and Jimmy Ba (2014) Adam: A method for stochastic optimization0.64422100%
6David Holtz, Ruben Lobel, Inessa Liskovich, and Sinan Aral (2020) Reducing interference bias in online marketplace pricing experiments0.51121100%
7Yuchen Hu and Stefan Wager (2022) Switchback experiments under geometric mixing0.51121100%
8Ramesh Johari, Hannah Li, Inessa Liskovich, and Gabriel Y Weintraub (2022) Experimental design in two-sided platforms: An analysis of bias0.51121100%
9Yan Wang and Shan Ba (2023) Producer-side experiments based on counterfactual interleaving designs for online recommender systems0.40511100%
10Peter M Aronow and Cyrus Samii (2017) Estimating average causal effects under general interference, with application to a social network experiment0.40511100%

Showing the top 10 of 65 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
12501.119960.40511