In this chapter, we will find out whether the stock prices will rise or fall depending on the rises and falls of markets in other time zones (such that their closing time is earlier than the stock in which we want to invest in). We will analyze the data from European markets that close about 3 or 4 hours before the American stock markets. From Quandl, we will get the data from the following European markets:

• WSE/OPONEO_PL
• WSE/VINDEXUS
• WSE/WAWEL
• WSE/WIELTON

And we will predict the closing rise and fall for the following American market: WIKI/SNPS.

We will download all the market data, view the downloaded graphs for the markets' closing values, and modify the data so that it can be trained on our networks. Then, we'll see how our networks perform on our assumptions.

The code and analysis techniques used in this chapter are inspired by Google's Cloud Datalab notebook found at https://github.com/googledatalab/notebooks/blob/master/samples/TensorFlow/Machine%20Learning%20with%20Financial%20Data.ipynbhere.

The steps are as follows:

1. Download the required data and modify it.
2. View the original and modified data.
3. Extract features from the modified data.
4. Prepare for training and test out the network.
5. Build the network.
6. Training.
7. Testing.