Deep Learning, Jumps, and Volatility Bursts
25 Pages Posted: 20 Sep 2019 Last revised: 14 Mar 2020
Date Written: September 12, 2019
We develop a new method that detects jumps nonparametrically in financial time series and significantly outperforms the current benchmark on simulated data. We use a long short- term memory (LSTM) neural network that is trained on labelled data generated by a process that experiences both jumps and volatility bursts. As a result, the network learns how to disentangle the two. Then it is applied to out-of-sample simulated data and delivers results that considerably differ from the benchmark: we obtain fewer spurious detection and identify a larger number of true jumps. When applied to real data, our approach for jump screening allows to extract a more precise signal about future volatility.
Keywords: Jumps, Volatility Burst, High-Frequency Data, Deep Learning, LSTM
JEL Classification: C14, C32, C45, C58, G17
Suggested Citation: Suggested Citation