Paid media and measurement · Randomized controlled field experiment with causal mediation analysis.
How Do Recommender Systems Lead to Consumer Purchases? A Causal Mediation Analysis of a Field Experiment
Xingyu Li, Jens Grahl, Oliver Hinz (2022). How Do Recommender Systems Lead to Consumer Purchases? A Causal Mediation Analysis of a Field Experiment. Information Systems Research. https://doi.org/10.1287/isre.2021.1074.
Plain-English take
Personalized recommendations increased purchase propensity 12.4% and basket value 1.7%; effects were largely mediated by consideration-set changes, especially breadth. For your marketing: Use to shape a locally controlled channel or message test; account for audience, timing and attribution limits before reallocating budget.
How much weight to give this
4/5 Strong design for its specific question
The 1–5 evidence-check score is a practical reading aid, not a formal peer review or a probability that a conclusion is true. It combines design strength (2 points), sample reporting (1), comparison/control clarity (1), and how much of the paper could be checked (1). Access affects how confidently this directory can assess a study, not the study's underlying quality. Blinding is reported separately because it is not relevant to every design.
Randomized controlled field experiment with causal mediation analysis.
Website of an online book retailer; consumer purchase behavior and consideration-set breadth/depth.
Judged from the publisher-described design and comparison; inspect the paper for complete analysis.
Publisher page and abstract were retrieved directly; full text was not assumed open.
Double-blind? Blinding was not established from the retrieved publisher record.
Research question
What the authors investigated
Through what causal paths do personalized recommendations induce purchases?
Design
Randomized controlled field experiment with causal mediation analysis.
Sample and setting
Website of an online book retailer; consumer purchase behavior and consideration-set breadth/depth.
Reported result
What the study found
Personalized recommendations increased purchase propensity 12.4% and basket value 1.7%; effects were largely mediated by consideration-set changes, especially breadth.
This is a paraphrase of the source. Check the original paper for definitions, estimates, statistical uncertainty and analysis details.
Scope and transfer
Limitations to keep in view
Online-book-retailer context; publisher abstract does not establish effects for other categories or platforms.
Possible founder application
Use to shape a locally controlled channel or message test; account for audience, timing and attribution limits before reallocating budget.
Evidence access
Publisher record and abstract retrieved; consult the linked paper for full methods and tables.
Publisher abstract reports design, setting, quantified effects and mediation mechanism. Direct publisher-page retrieval was recorded on 2026-10-09; this profile uses the publisher abstract/metadata and does not claim independent review of unavailable full text.
If only an abstract or metadata was available, the profile is limited to claims supported there. A paper's paywall does not change its evidentiary status, but it limits what we can substantiate from accessible text.