Search

High-Frequency Volatility Prediction for Bitcoin

Author(s)

Junyu Wei

Affiliation(s)

International Business School Suzhou at XJTLU, Suzhou, China

Abstract

Cryptocurrency markets operate continuously and generate high-frequency order book data that provides detailed information about market liquidity, depth, and order flow. However, the high dimensionality and volatility of limit order book data make short-term price prediction challenging. This study investigates the prediction of future mid-price movements for BTC/USDT using minute-level limit order book data from Binance. The dataset contains 741,600 order book snapshots collected from January 2022 to May 2023, with five price levels on both the bid and ask sides. We construct key order book features, including mid-price, bid-ask spread, order imbalance, and market depth, and develop classification models to predict price direction across multiple forecasting horizons. The study provides a baseline framework for high-frequency cryptocurrency price prediction and establishes a feature engineering pipeline that can be further extended using advanced deep learning architectures, including Transformer and DeepLOB models.

Keywords

Cryptocurrency; Bitcoin; Limit Order Book; High-Frequency Trading; Price Prediction; Order Imbalance; Deep Learning

References

[1]Bilokon, P. and Qiu, Y. (2023) 'Transformers versus LSTMs for electronic trading', arXiv preprint arXiv:2309.11400. [2]Cont, R. (2001) 'Empirical properties of asset returns: Stylized facts and statistical issues', Quantitative Finance, 1(2), pp. 223-236. [3]Cont, R., Kukanov, A. and Stoikov, S. (2014) 'The price impact of order book events', Journal of Financial Econometrics, 12(1), pp. 47-88. [4]Farooq, A., Uddin, M.I., Adnan, M., Alarood, A.A., Alsolami, E. and Habibullah, S. (2024) 'Interpretable multi-horizon time series forecasting of cryptocurrencies by leverage temporal fusion transformer', Heliyon, 10(22), e40142. [5]Gould, M.D., Porter, M.A., Williams, S., McDonald, M., Fenn, D.J. and Howison, S.D. (2013) 'Limit order books', Quantitative Finance, 13(11), pp. 1709-1742. [6]Kolm, P.N., Turiel, J. and Westray, N. (2023) 'Deep order flow imbalance: Extracting alpha at multiple horizons from the limit order book', Mathematical Finance, 33(4), pp. 1044-1081. [7]Letteri, I. (2025) 'A comparative analysis of statistical and machine learning models for outlier detection in Bitcoin limit order books', arXiv preprint arXiv:2507.14960. [8]Lim, B., Arik, S.O., Loeff, N. and Pfister, T. (2021) 'Temporal Fusion Transformers for interpretable multi-horizon time series forecasting', International Journal of Forecasting, 37(4), pp. 1748-1764. [9]Tsantekidis, A., Passalis, N., Tefas, A., Kanniainen, J., Gabbouj, M. and Iosifidis, A. (2017) 'Forecasting stock prices from the limit order book using convolutional neural networks', in Proceedings of the 2017 IEEE 19th Conference on Business Informatics (CBI), pp. 7-12. [10]Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L. and Polosukhin, I. (2017) 'Attention is all you need', in Advances in Neural Information Processing Systems, 30, pp. 5998-6008. [11]Wallbridge, J. (2020) 'Transformers for limit order books', arXiv preprint arXiv:2003.00130. [12]Zhang, Z., Zohren, S. and Roberts, S. (2019) 'DeepLOB: Deep convolutional neural networks for limit order books', IEEE Transactions on Signal Processing, 67(11), pp. 3001-3012.