Exploring the Advantages of Transformers for High-Frequency Trading
Machine learning return prediction in crypto, studied by Barez and co-authors in 2023 with a transformer. The abstract does not mention a benchmark, an out-of-sample test, transaction costs, multiple testing or the size of the universe.
“Ultimately, the performance of the HFformer and Long Short-Term Memory models are assessed and results indicate that the HFformer achieves a higher cumulative PnL than the LSTM when trading with multiple signals during backtesting.”
AssetCryptospot crypto
StrategyMachine learning
TechniqueTransformerrecurrent neural network
FrequencyIntraday
Also stated: Long-short
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 | |
|---|---|---|---|---|---|
| Meta-Learning Reinforcement Learning for Crypto-Return Prediction by Wang et al. | 2026 | ||||
| Cryptocurrency return prediction: A machine learning analysis by Li et al. | 2024 | ||||
| Utilizing RNN for Real-time Cryptocurrency Price Prediction and Trading Strategy Optimization by Tumpa and Maduranga | 2024 | ||||
| Constructing trading strategy ensembles by classifying market states by Balcerak and Schmelzer | 2020 | ||||
| Bitcoin Technical Trading With Artificial Neural Network by Nakano et al. | 2018 |