English

Nonlinear Dynamic Factor Analysis With a Transformer Network

Econometrics 2026-01-21 v1 Machine Learning

Abstract

The paper develops a Transformer architecture for estimating dynamic factors from multivariate time series data under flexible identification assumptions. Performance on small datasets is improved substantially by using a conventional factor model as prior information via a regularization term in the training objective. The results are interpreted with Attention matrices that quantify the relative importance of variables and their lags for the factor estimate. Time variation in Attention patterns can help detect regime switches and evaluate narratives. Monte Carlo experiments suggest that the Transformer is more accurate than the linear factor model, when the data deviate from linear-Gaussian assumptions. An empirical application uses the Transformer to construct a coincident index of U.S. real economic activity.

Keywords

Cite

@article{arxiv.2601.12039,
  title  = {Nonlinear Dynamic Factor Analysis With a Transformer Network},
  author = {Oliver Snellman},
  journal= {arXiv preprint arXiv:2601.12039},
  year   = {2026}
}

Comments

Working paper. 88 pages, 57 figures, 14 tables. Earlier versions circulated as "Nowcasting with a Transformer Network" (first version: 26 Oct 2024)

R2 v1 2026-07-01T09:08:54.139Z