An integrated early warning system for stock market turbulence

Abstract

This study constructs an integrated early warning system (EWS) that identifies and predicts stock market turbulence. Based on switching ARCH (SWARCH) filtering probabilities of the high volatility regime, the proposed EWS first classifies stock market crises according to an indicator function with thresholds dynamically selected by the two-peak method. An hybrid algorithm is then developed in the framework of a long short-term memory (LSTM) network to make daily predictions that alert turmoils. In the empirical evaluation based on ten-year Chinese stock data, the proposed EWS yields satisfying results with the test-set accuracy of 96.6% and on average 2.4 days of forewarned period. The model's stability and practical value in the real-time decision-making are also proven by the cross-validation and back-testing.

Are Crises Predictable? A Review of the Early Warning Systems in Currency and Stock Markets

“…The gap of cutoff optimization is further bridged according to the market turmoil level variation by imposing an automatically thresholding approach on the two-peak methodology theoretical basis (Rosenfeld and Torre, 1983;Ohtsu, 2007) on the SWARCH classifier. This dynamically adaptive classifier has been successfully verified in predicting stock crashes (Wang et al, 2020a). The other issue that is rarely mentioned in previous studies for EWS classifier construction is the variation of data frequency.…”

“…The predictive models that support EWS constructions will be clustered as three main branches: the logit/probit regression model -which classic methodology pioneers the EWS construction and keeps most prevailing in the crisis prediction studies (Eichengreen et al, 1995;Frankel and Rose, 1996;Berg and Pattillo, 1999b;Bussiere and Fratzscher, 2006;Candelon et al, 2014;Dawood et al, 2017); the indicator approachwhich provides an alternative nonparametric methodology to detect the leading factors and uses the refined factors to construct the crisis indicator (Kaminsky et al, 1998;Kaminsky and Reinhart, 1999;Lestano et al, 2004;Berg et al, 2005;Coudert and Gex, 2008;Rogoff, 2011, 2013;Peng and Bajona, 2008); the state-of-art machine learning and deep learning models (Nag and Mitra, 1999;Oh et al, 2006;Celik and Karatepe, 2007;Yu et al, 2010;Yoon and Park, 2014;Chatzis et al, 2018;Beutel et al, 2019;Wang et al, 2020a;Samitas et al, 2020) -which are not merely expert in modeling the data with significant non-linearity and non-normality, but barely subject to the data size as well. Comparing to the first two classic models, the stylized machine learning models generally perform best in forecasting ability, but meanwhile suffers the pain of deteriorating performance on out-of-samples as the model structure complexity is gained that leads serious over-fitting effect (Beutel et al, 2019;Holopainen and Sarlin, 2017) especially for low frequency data prediction.…”

“…In the study, we adopted AR(p)-SWARCH(K,q) model to classify the stock and currency price index volatility. Hamilton and Susmel (1994) Ct = 1 if F P Ht > c, Wang et al (2020a) where c is the two-peak method optimized cutoff value. currency Ct = 1 if 1 − (1 − F P Ht) 12 > 0.5, Abiad (2007) where 12 is the length of predictive months.…”

A Big Data Analytics Approach for Dynamic Feedback Warning for Complex Systems

“…Analysis. e occurrence of this round of stock disasters was a series of liquidity crises caused by leveraged funds entering the stock market, financing, and other account bursts [29][30][31].…”

The Impact of the COVID-19 Pandemic on the Unpredictable Dynamics of the Cryptocurrency Market

“…After the financial crisis that put the global economy into a panic in 2008, many studies have established a system to predict a crisis in advance by using big data and artificial intelligence (AI) [ 1 , 2 , 3 ]. The financial markets seems to have stabilized, but the World Health Organization (WHO) declared COVID-19 as a pandemic in 2020.…”