Deep Learning, Jumps, and Volatility Bursts

Jul, 2019 → Dec, 2021

Partner: Swissquote
Partner contact: Serge Kassibrakis
EPFL laboratory: Swiss Finance Institute @ EPFL
EPFL contact: Prof. Damir Filipovic, Alexis Marchal

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.

Topics:Machine LearningFinance