Neural Hidden Markov Model with Adaptive Granularity Attention for High-Frequency Order Flow Modeling

By Tianzuo Hu

Published 2026-03-20

Everscope rating

1834.3

Relevance to quantitative trading

9 / 10

Implementation complexity

8 / 10

Reproducibility

3 / 5

About this paper

Methodology: Adaptive Granularity Neural HMM (AGA-Neural HMM). Problem types: Time Series Forecasting, Classification, Market Making, Algorithmic Execution, Risk Management, Anomaly Detection, Density Estimation, Sequence-to-Sequence Learning.

arXiv:2603.20456 · Paper rankings

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