EXFormer: A Multi-Scale Trend-Aware Transformer with Dynamic Variable Selection for Foreign Exchange Returns Prediction

By Dinggao Liu, Robert Ślepaczuk, Zhenpeng Tang

Published 2026-01-21

Everscope rating

1293.8

Relevance to quantitative trading

9 / 10

Implementation complexity

8 / 10

Reproducibility

3 / 5

About this paper

Methodology: EXFormer. Problem types: Time Series Forecasting, Regression, Classification, Algorithmic Execution, Risk Management.

arXiv:2512.12727 · Paper rankings

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