Deep Learning for Asset Bubbles Detection

27 Pages Posted: 2 Mar 2020 Last revised: 9 Mar 2020

Date Written: February 3, 2020


We develop a methodology for detecting asset bubbles using a neural network. We rely on the theory of local martingales in continuous-time and use a deep network to estimate the diffusion coefficient of the price process more accurately than the current estimator, obtaining an improved detection of bubbles. We show the outperformance of our algorithm over the existing statistical method in a laboratory created with simulated data. We then apply the network classification to real data and build a zero net exposure trading strategy that exploits the risky arbitrage emanating from the presence of bubbles in the US equity market from 2006 to 2008. The profitability of the strategy provides an estimation of the economical magnitude of bubbles as well as support for the theoretical assumptions relied on.

Keywords: Bubbles, Strict local martingales, High-frequency data, Deep learning, LSTM

JEL Classification: C22, C45, C58, G12

Suggested Citation

Bashchenko, Oksana and Marchal, Alexis, Deep Learning for Asset Bubbles Detection (February 3, 2020). Swiss Finance Institute Research Paper No. 20-08, Available at SSRN: or

Oksana Bashchenko

Swiss Finance Institute - HEC Lausanne ( email )


Alexis Marchal (Contact Author)

EPFL ( email )

Station 5
Odyssea 1.04
1015 Lausanne, CH-1015
‭+41 21 693 09 23‬ (Phone)

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
PlumX Metrics