Publications

Published / Forthcoming

Fighting Fire with Fire: Infusing AI into Peer Review to Sustain Quality Scholarship

Hemant Bhargava et al. Management Science, 2026.

Examines how AI can support peer-review workflows as submission volume grows and reviewer capacity becomes increasingly scarce.

What Reviews Foretell about Opening Weekend Box Office Revenue: The Harbinger of Failure Effect in the Movie Industry

Pantelis Loupos, Yvette Peng, Sute Li, and Hao Hao. Marketing Letters, 2023.
Article | DOI

Shows that some reviewers systematically act as harbingers of failure: their positive pre-release reviews predict weaker opening-weekend box office performance.

Media coverage: UC Davis, Science X / Phys.org, Mirage News, EurekAlert!, Daily Mail

Platform Data Strategy

Hemant K. Bhargava, Olivier Rubel, Elizabeth J. Altman, Ramnik Arora, Jörn Boehnke, Kaitlin Daniels, Timothy Derdenger, Bryan Kirschner, Darin LaFramboise, Pantelis Loupos, Geoffrey Parker, and Adithya Pattabhiramaiah. Marketing Letters, 2020.
SSRN | DOI

Develops a strategic framework for how digital platforms collect, govern, share, and monetize data across users, firms, and ecosystem partners.

The Structure and Evolution of an Offline Peer-to-Peer Financial Network

Pantelis Loupos and Alexandros Nathan. Proceedings of the 10th Conference on Complex Networks, CompleNet 2019.
arXiv | DOI

Documents how Venmo’s peer-to-peer financial network forms and evolves, highlighting its connectivity, clustering, degree structure, and small-world properties.

Revise and Resubmit

Graph Neural Networks for Causal Inference Under Network Confounding

Michael Leung and Pantelis Loupos. Revise and resubmit at The Review of Economic Studies.
arXiv

Develops a GNN-based framework for estimating causal effects in observational network data when treatment selection and outcomes are confounded by high-dimensional network structure.

Network-Based Decision Support for Cold-Start User Valuation in P2P Platforms: The Role of Initial Community Structure

Pantelis Loupos and Moran Cerf. Revise and resubmit, Decision Support Systems.
SSRN

Shows how a new user’s initial network position can predict future activity and customer value before meaningful behavioral history exists.

Working Papers

The Shadow Value of Attention: Recommendation Ranking with Inventory Dynamics

Pantelis Loupos and Can Ürgün. To be submitted to Management Science.

Develops a multi-armed bandit framework for inventory-aware recommendation ranking, where exposure is allocated based on both demand potential and the shadow value of scarce inventory.

Modeling the Diffusion Dynamics of Crypto Tokens: A Dual-Process Approach to Adoption and Usage

Pantelis Loupos and Sriram Venkatesh. Working paper.

Develops a diffusion model for engagement-driven digital markets, showing how the interaction between cumulative adoption and active participation determines whether ecosystems scale, stall, or recover.