High frequency trading has been dominating finance industry recently. It brings big data and new problems in finance. How to estimate security volatility in high frequency trading remains a challenge in business analytics. In this study, we propose a novel section volatility estimation model and implement it via a big data analytics approach. The proposed method conquers the weakness of the conventional realized volatility by demonstrating the capability to capture both global and local behavior of volatility in the whole trading period besides robustness to the fine time intervals. To the best of our knowledge, this work is the first volatility study in high frequency trading by using big data analytics. It not only provides a fast and more accurate volatility estimation in high frequency trading, but also has its significance in finance theory and trading practice.
CITATION STYLE
Han, H., & Li, M. (2018). Big Data Analytics for High Frequency Trading Volatility Estimation. In Springer Proceedings in Business and Economics (pp. 351–359). Springer Science and Business Media B.V. https://doi.org/10.1007/978-3-319-72745-5_39
Mendeley helps you to discover research relevant for your work.