Working with Sequences

Let's look at another example to make the importance of sequence modeling clearer. The task is to predict the stock price for a company for the next 30 days. The data provided to you is the stock price for today. You can see this in the following plot, where the y-axis represents the stock price and the x-axis denotes the date. Is this data sufficient?

Figure 5.1: Stock price with just 1 day's data

Surely, one data point, that is, the price on a given day, is not sufficient to predict the price for the next 30 days. We need more information. Particularly, we need information about the past – how the stock price has been moving for the past few days/months/years. So, we ask for, and get, data for three years:

Figure 5.2: Stock price prediction using historical data

This seems much more useful, right? Looking at the past trend and some patterns in the data, we can make predictions on the...