The Inference-Compute Frontier and a Latency-Efficient Architecture for Limit Order Book Prediction

By C. Evans Hedges

Published 2026-06-24

Everscope rating

1605.1

Relevance to quantitative trading

9 / 10

Implementation complexity

5 / 10

Reproducibility

4 / 5

About this paper

Methodology: Inference-Compute Frontier Analysis and FastBiNLOB Architecture. Problem types: Classification, Time Series Forecasting, Market Making, Algorithmic Execution, Multi-task Learning.

arXiv:2606.25986 · Code · Paper rankings

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