EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY 4.0

Payment and transaction big data for economic nowcasting and decision support: a systematic review of predictive performance and real-time evaluation

Leonidas Theodorakopoulos, Alexandra Theodoropoulou, Christos Klavdianos, Spyridon Garmpis, Aristogiannis Garmpis

Frontiers in Big Data · 11.11.2026 · 9

DOI: 10.3389/fdata.2026.1729674 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Frontiers in Big Data, online erschienen am 11.11.2026. Verfasst von Leonidas Theodorakopoulos und 4 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Payment and transaction data offer timely signals of economic activity before conventional statistics become available. This study examines their contribution to economic nowcasting and the conditions under which they can serve as credible inputs to real-time decision support.

Methods

A systematic literature review was conducted in accordance with PRISMA 2020, covering peer-reviewed empirical studies published in English between January 2015 and August 2025. Searches primarily used Scopus and the Web of Science Core Collection, supplemented by publisher-platform and citation searches. A structured narrative synthesis examined predictive performance, data timeliness, modeling approaches, evaluation designs, and methodological quality.

Results

From 1,580 identified records, 11 studies were included. Comparative forecasting studies generally reported improved nowcasting performance for consumption, retail activity, and related macroeconomic variables when payment information was incorporated. However, the magnitude and timing of gains varied across countries, data sources, targets, and evaluation designs. Transaction data often provided valuable incremental information when conventional indicators were sparse, while absolute accuracy frequently improved as within-period observations accumulated. Bridge equations, MIDAS specifications, and factor or state-space models performed effectively across several applications; machine-learning methods provided additional gains in some settings. The strongest evidence combined realistic out-of-sample or real-time evaluation, explicit benchmarks, formal forecast comparisons, and transparent treatment of data vintages and information availability.

Discussion

Payment-based nowcasts can complement conventional indicators for monitoring, situational awareness, and short-horizon assessment. Their credibility depends on evaluation realism, transaction coverage, representativeness, and data stability. Heterogeneity and restricted data access limit comparability, reproducibility, and cross-country transferability. Whether decisions informed by these signals improve managerial or organizational outcomes remains an important question for future empirical research.

Zitieren

APA

Theodorakopoulos, L., Theodoropoulou, A., Klavdianos, C., Garmpis, S., & Garmpis, A. (2026). Payment and transaction big data for economic nowcasting and decision support: a systematic review of predictive performance and real-time evaluation. Frontiers in Big Data, 9. https://doi.org/10.3389/fdata.2026.1729674

Vancouver

Theodorakopoulos L, Theodoropoulou A, Klavdianos C, Garmpis S, Garmpis A. Payment and transaction big data for economic nowcasting and decision support: a systematic review of predictive performance and real-time evaluation. Frontiers in Big Data. 2026;9. doi:10.3389/fdata.2026.1729674

BibTeX
@article{Theodorakopoulos2026,
  author = {Theodorakopoulos, Leonidas and Theodoropoulou, Alexandra and Klavdianos, Christos and Garmpis, Spyridon and Garmpis, Aristogiannis},
  title = {Payment and transaction big data for economic nowcasting and decision support: a systematic review of predictive performance and real-time evaluation},
  journal = {Frontiers in Big Data},
  year = {2026},
  volume = {9},
  doi = {10.3389/fdata.2026.1729674}
}
Kostenlos starten →