B2B growth and sales · Randomized field experiment comparing collaborative-filter recommendations with no recommendations; product/category analyses.
How Do Recommender Systems Affect Sales Diversity? A Cross-Category Investigation via Randomized Field Experiment
Daniel Lee, Kartik Hosanagar (2019). How Do Recommender Systems Affect Sales Diversity? A Cross-Category Investigation via Randomized Field Experiment. Information Systems Research. https://doi.org/10.1287/isre.2018.0800.
Plain-English take
Traditional collaborative filtering reduced aggregate sales diversity; purchase-based CF had larger effects than view-based; niche items gained absolutely but lost share. For your marketing: Use as a mechanism or sales-process design reference. Validate the relationship in your own deal size, buying committee and sales cycle.
How much weight to give this
4.5/5 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 field experiment comparing collaborative-filter recommendations with no recommendations; product/category analyses.
Top North American retailer; 82,290 products and 1,138,238 users.
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
How do collaborative recommenders affect aggregate and individual sales diversity?
Design
Randomized field experiment comparing collaborative-filter recommendations with no recommendations; product/category analyses.
Sample and setting
Top North American retailer; 82,290 products and 1,138,238 users.
Reported result
What the study found
Traditional collaborative filtering reduced aggregate sales diversity; purchase-based CF had larger effects than view-based; niche items gained absolutely but lost share.
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
One top North American retailer and collaborative-filter designs; aggregate diversity can differ from individual consumption diversity.
Possible founder application
Use as a mechanism or sales-process design reference. Validate the relationship in your own deal size, buying committee and sales cycle.
Evidence access
Publisher record and abstract retrieved; consult the linked paper for full methods and tables.
Publisher abstract states the randomization, scale and four reported findings. 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.