Predictable markets? A news-driven model of the stock market

Article type: Research Article

Authors: Gusev, Maxim^a | Kroujiline, Dimitri^{b; *} | Govorkov, Boris^a | Sharov, Sergey V.^c | Ushanov, Dmitry^d | Zhilyaev, Maxim^e

Affiliations: [a] IBC Quantitative Strategies, Tärnaby, Sweden | [b] LGT Capital Partners, Pfäffikon, Switzerland | [c] N.I. Lobachevsky State University, Advanced School of General & Applied Physics, Nizhny Novgorod, Russia | [d] Department of Mechanics and Mathematics, Moscow State University, Moscow, Russia | [e] Mozilla Corporation, Mountain View, CA, USA

Correspondence: [*] Corresponding author: Dimitri Kroujiline, LGT Capital Partners, Pfäffikon, Switzerland. Tel.: +41 55 415 9856; Fax: +41 55 415 9898; E-mails: dimitri.kroujiline@lgt.com; URL: www.ibctrends.com (M. Gusev, B. Govorkov); www.lgt-capital-partners.com (D. Kroujiline); www.unn.ru (S.V. Sharov); www.math.msu.su (Ushanov); www.mozilla.org (M. Zhilyaev).

Abstract: We attempt to explain stock market dynamics in terms of the interaction among three variables: market price, investor opinion and information flow. We propose a framework for such interaction and apply it to build a model of stock market dynamics which we study both empirically and theoretically. We demonstrate that this model replicates observed market behavior on all relevant timescales (from days to years) reasonably well. Using the model, we obtain and discuss a number of results that pose implications for current market theory and offer potential practical applications.

Keywords: Stock market, market dynamics, return predictability, news analysis, language patterns, investor behavior, herding, business cycle, sentiment evolution, reference sentiment level, volatility, return distribution, Ising, agent-based models, price feedback, nonlinear dynamical systems

DOI: 10.3233/AF-150042

Journal: Algorithmic Finance, vol. 4, no. 1-2, pp. 5-51, 2015