Augmenting Neural Networks With Time‐Varying Weights

William Rudd, Howard Bondell and Jeremy Silver

Journal of Forecasting, 2026, vol. 45, issue 1, 22-28

Abstract: In the macroeconomic forecasting community, there is increasing interest in machine learning methods that can extract nonlinear predictive content from large datasets with a high number of predictors. Meanwhile, time‐varying parameter (TVP) models are known to flexibly model time series by allowing regression coefficients to vary over time. This paper generalizes neural networks to allow for time variation of the weights of the final layer. The variance components of the time‐varying weights are estimated alongside the fixed network weights via an EM algorithm. The result is the time‐varying neural network (TVNN), a fully supervised, nonlinear model, which combines the desirable properties of classical econometric approaches with the predictive capacity of neural networks. The TVNN model yields improved forecasts over similarly tuned feedforward neural networks with fixed weights, recurrent network architectures, and benchmark autoregressive models on time series from the popular FRED‐MD database.

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1002/for.70014

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wly:jforec:v:45:y:2026:i:1:p:22-28

Access Statistics for this article

Journal of Forecasting is currently edited by Derek W. Bunn

More articles in Journal of Forecasting from John Wiley & Sons, Ltd.
Bibliographic data for series maintained by Wiley Content Delivery ().