---
title: Deep Learning Models in Central Bank Forecasting
url: https://www.ml-quant.com/papers/repec/ptu-wpaper-w202612/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-10-30
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: RePEc:ptu:wpaper:w202612
source_url: https://econpapers.repec.org/RePEc:ptu:wpaper:w202612
featured: 2026-10-30
citations: unknown
topic: ML & AI Methods
---


# Deep Learning Models in Central Bank Forecasting

Pretrained time-series foundation models match or outperform benchmarks on selected inflation and nowcasting targets but add limited gains for labor-market aggregates or irregular series.

- Source: https://econpapers.repec.org/RePEc:ptu:wpaper:w202612
- Identifier: RePEc:ptu:wpaper:w202612
- Released: 2026-10-26
- First featured: Quant Letter No. 137 (2026-10-30): https://www.ml-quant.com/issues/2026-10-30/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: ML & AI Methods
- Authors: Paulo Júlio

## Related

- [KiT: A Foundation Model for Financial Time-Series Forecasting using DiffusionTransformers](https://www.ml-quant.com/papers/arxiv/2609.34507/): Diffusion transformer foundation model reformulates candlestick prediction as conditional trajectory generation, achieving 0.057 mean return RankIC across markets and timescales.
- [Explainable Machine Learning for Basel and IFRS 9 Credit Risk: A Placebo-Controlled Test of Narrative Features](https://www.ml-quant.com/papers/ssrn/7622180/): A placebo test reveals that features like central bank tone can raise credit model accuracy merely by indicating when loans were made, not by predicting defaults.
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://www.ml-quant.com/papers/arxiv/2405.21060/): The research identifies a link between state-space models and Transformers in deep learning, leading to the creation of a faster language modeling architecture, Mamba-2.
- [Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models](https://www.ml-quant.com/papers/arxiv/2501.01423/): The paper proposes a new model, VA-VAE, that aligns the latent space with pre-trained vision foundation models, enabling faster convergence of Diffusion Transformers in high-dimensional latent spaces and achieving top performance on ImageNet 256x256 generation.
- [SOAP: Improving and Stabilizing Shampoo using Adam](https://www.ml-quant.com/papers/arxiv/2409.11321/): A new algorithm, SOAP, enhances the computational efficiency of the Shampoo preconditioning method in deep learning tasks, reducing iterations and time, with an online implementation available.
- [Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models](https://www.ml-quant.com/papers/arxiv/2411.04996/): The Mixture-of-Transformers (MoT) is a sparse multi-modal transformer architecture that reduces pretraining costs and allows modality-specific processing with global self-attention.