JOURNAL ARTICLE

Wasserstein barycenter for link prediction in temporal networks.

  • Published In: Journal of the Royal Statistical Society: Series A (Statistics in Society), 2024, v. 187, n. 1. P. 178 1 of 3

  • Database: Business Source Ultimate 2 of 3

  • Authored By: Spelta, Alessandro; Pecora, Nicolò 3 of 3

Abstract

The article focuses on a flexible probabilistic methodology for forecasting links in weighted temporal networks using Wasserstein barycentric coordinates from optimal transport theory. This approach estimates the evolving dynamics of links by interpolating network sequences and computing the probability distribution of future link weights, including quantile forecasts. The methodology is tested on the worldwide Foreign Direct Investments (FDI) network and the World Trade Network, showing superior performance in quantile forecasts compared to alternative models and comparable accuracy in point forecasts. The study also finds that incorporating geographical distance constraints improves the prediction of link weights more effectively than economic distance.

Additional Information

  • Source:Journal of the Royal Statistical Society: Series A (Statistics in Society). 2024/01, Vol. 187, Issue 1, p178
  • Document Type:Article
  • Subject Area:Business and Management
  • Publication Date:2024
  • ISSN:0964-1998
  • DOI:10.1093/jrsssa/qnad088
  • Accession Number:174783720
  • Copyright Statement:Copyright of Journal of the Royal Statistical Society: Series A (Statistics in Society) is the property of Oxford University Press / USA and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Looking to go deeper into this topic? Look for more articles on EBSCOhost.