Neural Networks in Narrow Stock Markets

Abstract

Narrow markets are typically considered those that due to limited liquidity or peculiarities in its investor base, such as a particularly high concentration of retail investors, make the stock market less efficient and arguably less predictable. We show in this article that neural networks, applied to narrow markets, can provide relatively accurate forecasts in narrow markets. However, practical considerations such as potentially suboptimal trading infrastructure and stale prices should be taken into considerations. There is ample existing literature describing the use of neural network as a forecasting tool in deep stock markets. The application of neural networks to narrow markets have received much less literature coverage. It is however an important topic as having reliable stock forecasting tools in narrow markets can help with the development of the local stock market, potentially also helping the real economy. Neural networks applied to moderately narrow markets generated forecasts that appear to be comparable, but typically not as accurate, as those obtained in deep markets. These results are consistent across a wide range of learning algorithms and other network features such as the number of neurons. Selecting the appropriate network structure, including deciding what training algorithm to use, is a crucial step in order to obtain accurate forecasts.