Causal Inference under Algorithmic Interference: Identification and Estimation without SUTVA in Platform Economies

Jakub Ryłow

No 2026-7, Working Papers from Faculty of Economic Sciences, University of Warsaw

Abstract: The Stable Unit Treatment Value Assumption (SUTVA) fails systematically in platform economies where a deterministic algorithm mediates all interactions, making interference structural and mechanistically knowable. We introduce algorithmic interference — a structural potential-outcomes model in which spillovers flow through the platform's known decision rule — and construct the Debiased Algorithmic Instrumental Variable (DAIV) estimator: a cross-fitted semiparametric procedure combining Double Machine Learning with the IV equation implied by the algorithmic mechanism. Under local algorithmic monotonicity (LAM), both the ATE and CATE are point identified; without LAM the sharp identified set is characterised. DAIV is sqrt(n)-consistent, asymptotically normal, and semiparametrically efficient, with a formal LAM test supplied. A synthetic ride-sharing example (n = 10,000) shows that standard DML overstates the treatment effect by 52% relative to DAIV; a Hausman-type specification test strongly rejects no algorithmic interference.

Keywords: algorithmic interference; SUTVA; potential outcomes; causal identification; double machine learning; platform economies; instrumental variables; semiparametric efficiency; partial identification (search for similar items in EconPapers)
JEL-codes: C14 C21 C26 D47 L86 (search for similar items in EconPapers)
Pages: 23 pages
Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.wne.uw.edu.pl/download_file/7130/0 First version, 2026 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:war:wpaper:2026-7

Access Statistics for this paper

More papers in Working Papers from Faculty of Economic Sciences, University of Warsaw Contact information at EDIRC.
Bibliographic data for series maintained by Jacek Rapacz ().