Stock market price prediction is one of the most challenging tasks. One of the major reasons is noise and the volatile features of this type of dataset. Therefore, how to predict stock price movement accurately is still an open question for the modern trading world. However classical machine learning algorithms, such as Support vector machines, decision trees, and tree ensembles (for example, random forest and gradient-boosted trees), have been used in the last decade.
However, stock market prices have severe volatility and a historical perspective, which make them suited for time series analysis. This also challenges those classical algorithms, since long-term dependencies cannot be availed using those algorithms. Considering these challenges and the limitations of existing algorithms, in this chapter, we will see how to develop a real...