Temporal Kolmogorov-Arnold Networks (T-KAN) for High-Frequency Limit Order Book Forecasting: Efficiency, Interpretability, and Alpha-Decay

By Ahmad Makinde

Published 2026-07-21

Everscope rating

1827

Relevance to quantitative trading

8 / 10

Implementation complexity

7 / 10

Reproducibility

4 / 5

About this paper

Methodology: Temporal Kolmogorov-Arnold Network (T-KAN). Problem types: Classification, Time Series Forecasting, Imbalanced Learning, Algorithmic Execution.

arXiv:2601.02310 · Code · Paper rankings

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