Bitcoin Direction Models with Confidence-Based Risk Control

Summary

This study uses internal Bitcoin network data and external features to predict daily price direction with multiple machine learning models. It evaluates those forecasts through a trading strategy on unseen observations gathered during the first quarter of 2021. A binary signal produces returns reported as comparable to buy-and-hold over the three-month test period.

The strategy also uses prediction confidence as a risk tolerance input, adapting trading decisions according to how certain the model is. The authors report that this version outperformed buy-and-hold in the stated period. These results are limited to one asset and a short historical evaluation window; the excerpt provides no detail on costs, risk-adjusted performance, model selection, or robustness across other regimes. The reported outcome therefore motivates further testing rather than establishing durable live-trading performance.

Key ideas

• The models combine Bitcoin network features with external inputs to classify daily direction.
• Performance is evaluated through a trading strategy on unseen data from the first quarter of 2021.
• Using prediction confidence to adjust risk tolerance is reported to improve results against buy-and-hold.
• The short, single-period evaluation does not establish robustness across market regimes or live trading.

Tags

# Exploration of Algorithmic Trading Strategies for the Bitcoin Market


# Exploration of Algorithmic Trading Strategies for the Bitcoin Market









Bitcoin is firmly becoming a mainstream asset in our global society. Its highly volatile nature has traders and speculators flooding into the market to take advantage of its significant price swings in the hope of making money. This work brings an algorithmic trading approach to the Bitcoin market to exploit the variability in its price on a day-to-day basis through the classification of its direction. Building on previous work, in this paper, we utilise both features internal to the Bitcoin network and external features to inform the prediction of various machine learning models. As an empirical test of our models, we evaluate them using a real-world trading strategy on completely unseen data collected throughout the first quarter of 2021. Using only a binary predictor, at the end of our three-month trading period, our models showed an average profit of 86\%, matching the results of the more traditional buy-and-hold strategy. However, after incorporating a risk tolerance score into our trading strategy by utilising the model's prediction confidence scores, our models were 12.5\% more profitable than the simple buy-and-hold strategy. These results indicate the credible potential that machine learning models have in extracting profit from the Bitcoin market and act as a front-runner for further research into real-world Bitcoin trading.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.