Fixed link

Forecasting stock market returns over multiple time horizons

Dimitri Kroujiline, Maxim Gusev, Dmitry Ushanov, Sergey V. Sharov and Boris Govorkov

posted on 18 August 2015

download (1364 views, 1577 download, 1 comments)

In this paper we seek to demonstrate the predictability of stock market returns and explain the nature of this return predictability. To this end, we further develop the news-driven analytic model of the stock market derived in Gusev et al. (2015). This enables us to capture market dynamics at various timescales and shed light on mechanisms underlying certain market behaviors such as transitions between bull- and bear markets and the self-similar behavior of price changes. We investigate the model and show that the market is nearly efficient on timescales shorter than one day, adjusting quickly to incoming news, but is inefficient on longer timescales, where news may have a long-lasting nonlinear impact on dynamics attributable to a feedback mechanism acting over these horizons. Using the model, we design the prototypes of algorithmic strategies that utilize news flow, quantified and measured, as the only input to trade on market return forecasts over multiple horizons, from days to months. The backtested results suggest that the return is predictable to the extent that successful trading strategies can be constructed to harness this predictability.


Here we further develop the ideas of our paper published in the last issue of Algorithmic Finance and posted here on 08 September 2014. We hope you enjoy the reading it and we welcome your feedback. - The authors