We started the chapter by introducing time series data and the traditional approaches to solving them. We gave you an overview of deep learning networks and information on how they learn. Furthermore, we introduced the MXNet R package. Then we prepared our stock market data so that our deep learning network could consume it. Finally, we built two deep learning networks, one for regression, where we predicted the actual closing price of the stock, and one for classification, where we predicted whether the stock price would move up or down.
In the next chapter, we will deal with sentiment mining. We will show how to extract tweets in R, process them and use a dictionary based method to find the sentiments of the tweets. Finally using those scored tweets as datasets we will build a Naive Bayes model based on Kernel density estimate.