MACRO-AWARE TIME SERIES FORECASTING VIA HIERARCHICAL MIXED-FREQUENCY ATTENTION MODELS

By Daniel Cunha Oliveira, Kieran Wood, Stefan Zohren, Mihai Cucuringu, André Fujita

Published 2026-06-02

Everscope rating

1549

Relevance to quantitative trading

9 / 10

Implementation complexity

7 / 10

Reproducibility

3 / 5

About this paper

Methodology: HANET (Hierarchical Attention Network). Problem types: Time Series Forecasting, Portfolio Optimization, Few-shot Learning, Risk Management, Algorithmic Execution.

arXiv:2606.00624 · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.