Cryptocurrency return prediction: A machine learning analysis
A 2024 paper by Li and co-authors on machine learning return prediction in crypto, using a feedforward neural network: the abstract mentions profits and leaves out a benchmark, an out-of-sample test, transaction costs, multiple testing and the size of the universe.
“Notably, portfolios constructed based on neural networks achieve the highest cumulative returns.”
AssetCryptospot crypto
StrategyMachine learning
TechniqueFeedforward networktree ensemble
ClaimProfit
Also stated: Long-short, Long-only
Missing from abstract: benchmark, out-of-sample test, costs, multiple testing, universe
Institutional-grade audit of this strategy.
£5 — Request the audit- Audit of the paper claims accounting for costs, luck, crises, originality, geography, etc.
- Reproduction code integratable into Bloomberg, IBKR, etc.
- Bias-free datasets for backtesting included
- Delivered in 2 working days
The paper's neighbourhoodMachine learning return prediction by year
The family is counted across the whole universe. Asset, method and authors are counted inside the family.
| Similar papers | citation | same method | same asset | same authors | |
|---|---|---|---|---|---|
| Beyond the Hype: A Multi-Layer Machine Learning Framework for Cryptocurrency Return Forecasting by Khoso | 2026 | ||||
| Meta-Learning Reinforcement Learning for Crypto-Return Prediction by Wang et al. | 2026 | ||||
| Evaluating COVID 19 Feature Contributions to Bitcoin Return Forecasting: Methodology Based on LightGBM and Genetic Optimization by Mahmoud and Velichko | 2025 | ||||
| Utilizing RNN for Real-time Cryptocurrency Price Prediction and Trading Strategy Optimization by Tumpa and Maduranga | 2024 | ||||
| Exploring the Advantages of Transformers for High-Frequency Trading by Barez et al. | 2023 |