Machine Learning-Based Bitcoin Trading Under Transaction Costs: Evidence From Walk-Forward Forecasting

By Andrei Bysik, Robert Ślepaczuk

Published 2026-05-19

Everscope rating

1803.7

Relevance to quantitative trading

9 / 10

Implementation complexity

7 / 10

Reproducibility

3 / 5

About this paper

Methodology: Walk-Forward Forecasting with Cost-Aware Execution Filter. Problem types: Time Series Forecasting, Algorithmic Execution, Portfolio Optimization, Risk Management.

arXiv:2606.00060 · Paper rankings

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