- Term Papers and Free Essays

Forecasting Stock Market Crisis Events Using Deep and Statistical Machine Learning Techniques

Essay by   •  December 23, 2018  •  Research Paper  •  14,231 Words (57 Pages)  •  120 Views

Essay Preview: Forecasting Stock Market Crisis Events Using Deep and Statistical Machine Learning Techniques

Report this essay
Page 1 of 57

Forecasting stock market crisis events using deep and statistical machine learning techniques

Sotirios P. Chatzis a , , Vassilis Siakoulis b , Anastasios Petropoulos b , Evangelos Stavroulakis b , Nikos Vlachogiannakis b

a Department of Electrical Engineering, Computer Engineering and Informatics, Cyprus University of Technology, Limassol 3036, Cyprus b Bank of Greece, Banking Supervision Division, 3 Amerikis Str., Athens 10250, Greece

a r t i c l e i n f o

Article history: Received 10 April 2018 Revised 13 June 2018 Accepted 14 June 2018 Available online 28 June 2018

Keywords: Stock market crashes Forecasting Random forests Support vector machines Deep learning XGBoost

a b s t r a c t

This work contributes to this ongoing debate on the nature and the characteristics of propagation chan- nels of crash events in international stock markets. Specifically, we investigate transmission mechanisms across stock markets along with effects from bond and currency markets. Our approach comprises a solid forecasting mechanism of the probability of a stock market crash event in various time frames. The de- veloped approach combines different machine learning algorithms which are presented with daily stock, bond and currency data from 39 countries that cover a large spectrum of economies. Specifically, we leverage the merits of a series of techniques including Classification Trees, Support Vector Machines, Random Forests, Neural Networks, Extreme Gradient Boosting, and Deep Neural Networks. To the best of our knowledge, this is the first time that Deep Learning and Boosting approaches are considered in the literature as a means of predicting stock market crisis episodes. The independent variables included in our data contain information regarding both the two fundamental linkage channels through which financial contagion can be initiated: returns and volatility. We apply a suite of machine learning algo- rithms for selecting the most relevant variables out of a large set of proposed ones. Finally, we employ bootstrap sampling for adjusting the imbalanced nature of the available fitting dataset. Our experimental results provide strong evidence that stock market crises tend to exhibit persistence. We also find signif- icant evidence of interdependence and cross-contagion effects among stock, bond and currency markets. Finally, we show that the use of Deep Neural Networks significantly increases the classification accuracy, while offering a robust way to create a global systemic early warning tool that is more efficient and risk-sensitive than the currently established ones. Thus, central banks may use these tools to early adjust their monetary policy, so as to ensure financial stability.

© 2018 Elsevier Ltd. All rights reserved.

1. Introduction

A global financial crisis can emerge from a series of local or/and regional market shocks, which evolve into a worldwide economic crisis due to the interconnectedness of the financial markets. For example, the Asian crisis in 1997 initially originated in Thailand; subsequently, it propagated to other Asian countries, and eventu- ally made it to the financial markets of the United States of Amer- ica and Europe ( Kaminsky, Lizondo, & Reinhart, 1998 ). In other cases, a crisis may start from a single economy whose size is large

Corresponding author.

E-mail addresses: , (S.P. Chatzis), (V. Siakoulis), (A. Petropoulos), (E. Stavroulakis), (N. Vlachogiannakis).

enough to generate turbulence in other countries. This is the case, for instance, with the subprime crisis that started in the United States and evolved into a sovereign debt crisis in several European countries.

The observation that an economic crisis is manifested by a sub- sequent recession ( Barro & Ursua, 2009; Bluedorn, Decressin, & Terrones, 2013; Estrella & Mishkin, 1996; Farmer, 2012 ) renders re- liable Early Warning Systems (EWSs) valuable tools for policymak- ers, in their effort to curtail contagion risk and, in extreme cases, even preempt a global economic crisis. An EWS must be capable of producing clear signals as to whether an economic crisis is immi- nent, complementing the expert judgment of policymakers. Hence, EWS systems facilitate policy makers in unveiling vulnerabilities of the economy and taking precautionary actions to diminish the risks that can trigger a crisis. Certainly, there is always a trade- off between developing EWSs that are capable of predicting a lot 0957-4174/© 2018 Elsevier Ltd. All rights reserved.

Contents lists available at ScienceDirect

Expert Systems With Applications

journal homepage:

Expert Systems With Applications 112 (2018) 353–371

354 S.P. Chatzis et al. / Expert Systems With Applications 112 (2018) 353–371

of alarms for an imminent crisis, at the expense of some of them being wrong (false-alarms), and EWSs that predict rather too few signals of impending crises, at the expense of missing a major cri- sis event. Optimally, an EWS should let no crisis events go unno- ticed, while minimizing the number of generated false-alarms. It goes without saying that the cost of not signaling a global crisis is significantly higher than that of an incorrect alarm.

At the same time, the incorporation of the probability of a worldwide crisis in decisions related to asset al.location ( Kole, Koedijk, & Verbeek, 2006 ) can substantially benefit investors. Indeed, this is the case since a global crisis significantly curtails di- versification benefits, as worldwide markets move in the same di- rection. In addition, any hedging strategies may become ineffective ( Ibragimov & Johan, 2007 ) due to the structural changes in the ob- served correlations among asset classes. Indeed, during periods of high volatility in bear markets, correlations increase across assets ( Longin & Solnik, 2001 ). Thus, as the markets cannot quickly cor- rect any disruptions in their function, it becomes even more imper- ative for regulators to intervene so as to restore financial stability.



Download as:   txt (88.7 Kb)   pdf (730 Kb)   docx (1 Mb)  
Continue for 56 more pages »
Only available on
Citation Generator

(2018, 12). Forecasting Stock Market Crisis Events Using Deep and Statistical Machine Learning Techniques. Retrieved 12, 2018, from

"Forecasting Stock Market Crisis Events Using Deep and Statistical Machine Learning Techniques" 12 2018. 2018. 12 2018 <>.

"Forecasting Stock Market Crisis Events Using Deep and Statistical Machine Learning Techniques.", 12 2018. Web. 12 2018. <>.

"Forecasting Stock Market Crisis Events Using Deep and Statistical Machine Learning Techniques." 12, 2018. Accessed 12, 2018.