Putting our knowledge to use

Now that we have achieved a good understanding of how an LSTM works and what kind of tasks they particularly tend to excel at, it is time to implement a real-world example. Of course, time series data can appear in a vast array of settings, ranging from sensor data from industrial machinery to spectrometric data representing light arriving from distant stars. Today, however, we will simulate a more common, yet notorious, use case. We will implement an LSTM to predict the movement of stock prices. For this purpose, we will employ the Standard & Poor (S&P) 500 dataset, and select a random stock to prepare for sequential modeling. The dataset can be found on Kaggle, and comprises historical stock prices (opening, high, low, and closing prices) for all current S&P 500 large capital companies traded on the American stock market.

...