EconBase
← All papers

Estimating Treatment Effects under Recommender Interference: A Structured Neural Networks Approach

Ruohan Zhan, Shichao Han, Yuchen Hu, Zhenling Jiang

arXiv 20 Jun 2024 · Econometrics · 3 citations (OpenAlex)

arXiv:2406.14380 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Recommender systems are essential for content-sharing platforms by curating personalized content. To evaluate updates to recommender systems targeting content creators, platforms frequently rely on creator-side randomized experiments. The treatment effect measures the change in outcomes when a new algorithm is implemented compared to the status quo. We show that the standard difference-in-means estimator can lead to biased estimates due to recommender interference that arises when treated and control creators compete for exposure. We propose a "recommender choice model" that describes which item gets exposed from a pool containing both treated and control items. By combining a structural choice model with neural networks, this framework directly models the interference pathway while accounting for rich viewer-content heterogeneity. We construct a debiased estimator of the treatment effect and prove it is $\sqrt n$-consistent and asymptotically normal with potentially correlated samples. We validate our estimator's empirical performance with a field experiment on Weixin short-video platform. In addition to the standard creator-side experiment, we conduct a costly double-sided randomization design to obtain a benchmark estimate free from interference bias. 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.

Citation extraction

44
references
77
in-text mentions
44
distinct cited
0
self-citations
24,608
main-text words

appendix boundary found by none_found · 100% 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
1Farrell MH, Liang T, Misra S (2021) a) Deep learning for individual heterogeneity: An automatic inference framework1.000143100%
2Chernozhukov V, Chetverikov D, Demirer M, Duflo E, Hansen C, Newey W… (2018) Double/debiased machine learning for treatment and structural parameters1.00053100%
3Goli A, Lambrecht A, Yoganarasimhan H (2023) A bias correction approach for interference in ranking experiments0.92843100%
4Johari R, Li H, Liskovich I, Weintraub GY (2022) Experimental design in two-sided platforms: An analysis of bias0.92843100%
5Chernozhukov V, Demirer M, Lewis G, Syrgkanis V (2019) Semi-parametric efficient policy learning with continuous actions0.84333100%
6Farias V, Li H, Peng T, Ren X, Zhang H, Zheng A (2023) Correcting for interference in experiments: A case study at douyin0.64422100%
7Foster DJ, Syrgkanis V (2023) Orthogonal statistical learning0.64422100%
8Sävje F, Aronow P, Hudgens M (2021) Average treatment effects in the presence of unknown interference0.64422100%
9Ye Z, Zhang Z, Zhang D, Zhang H, Zhang RP (2023) b) Deep learning based causal inference for large-scale combinatorial experiments: Theory and empirical evidence0.64422100%
10Bright I, Delarue A, Lobel I (2022) Reducing marketplace interference bias via shadow prices0.51121100%

Showing the top 10 of 44 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
12501.119960.51121
2ARMA-Design: Optimal Treatment Allocation Strategies for A/B Testing in Partially Observable Experiments0.40511
3Experimental Design for Matching0.40511
4Personalized Policy Learning through Discrete Experimentation: Theory and Empirical Evidence0.40511