Stock market prediction has been a challenging problem that has caught the attention of many researchers. Building an accurate predictive model would contribute greatly to the economic stability of the countries. Technical Analysis, Linear models, Machine Learning are just a few examples of the different approaches that have been tried to predict the stock market. Some researchers introduced into their models features based on sentiment analysis of social media tweets, proving that accounting for investors’ behavior can help predictive models. In addition to investors’ sentiment, it is possible that incorporating theory-driven behavioral insights into predictive models may also improve performance.
In this work we show the effect of incorporating behavioral features to an Attentive LSTM network for stock prediction.