Hands-On Deep Learning with R

Understanding common methods for stock market prediction

In this chapter, we will learn about a different type of neural network called an RNN. In particular, we will apply a type of RNN known as an LSTM model to predict stock prices. Before we begin, let's first look at some common methods of predicting stock prices to better understand the problem.

Predicting stock prices is a time-series problem. With most other machine learning problems, variables can be split at random and used in training and test datasets, but this is not possible when solving a time-series problem. The variables must remain in order. The features to solve the problem can be found in the sequence of events and, consequently, the chronology of how events occurred must ...