Events

CILVR Seminar: Causal Inference, Unmeasured Confounding and Estimating Welfare in Digital Platforms

Speaker: Jaume Vives-i-Bastida (NYU)

Location: 60 Fifth Avenue, Room 7th Floor Open Space
Videoconference link: https://nyu.zoom.us/j/98954373715

Date: Wednesday, October 28, 2026

Abstract: Digital platforms bring together consumers and producers, but how they do so can have deep implications for competition and welfare. For example, platforms can influence prices by varying what commissions they charge to consumers or to merchants, but they can also directly shape demand through recommendation systems. Understanding the implications of different platform choices is crucial to both policy makers and market participants. In this talk, I will investigate this in the context of a food delivery platform that bargains with restaurants to set commission fees and adjudicate higher ranking slots in the consumer search wall. In doing so, I will first highlight a general causal inference problem in estimating the causal effects of promotional contracts in the presence of unmeasured confounding and present methodological work on how to construct Synthetic Instrumental Variables to solve this problem. Then, I will show how to use the causal estimates in combination with a structural model of the platform to disentangle the different effects of commission fees, search ranking preferencing and consumer and producer entry into the platform. The empirical results highlight the importance of "anchor" producers that bring in new consumers and need to be attracted using preferential contracts. 

Bio: Jaume Vives-i-Bastida is an Economics and Data Science researcher primarily working in combining ML and Econometrics for policy evaluation and platform economics. Currently, he is an Assistant Professor of Economics and Data Science at NYU, following a year as a Postdoc at Stanford GSB and the Stanford Causal Science Center collaborating with Airbnb. In 2025, he received a PhD in Economics and Statistics from MIT. During the PhD he was a Meta Research PhD Fellow and a La Caixa Fellow. Previously, he obtained a BSc. in Econometrics and Mathematical Economics from the LSE (First Class Honours) and worked as a research professional at the University of Chicago Booth School of Business. He also has experience designing causal inference methods at Google, Quantco, and as a consultant for Ivalua (Catalan Government).