In practice, we need to explore variations of the design options outlined previously because we can rarely be sure from the outset of which network architecture best suits the data.
The GridSearchCV class provided by scikit-learn that we encountered in Chapter 6, The Machine Learning Process, conveniently automates this process. Just be mindful of the risk of false discoveries and keep track of how many experiments you are running to adjust the results accordingly.
In this section, we will explore various options to build a simple feedforward neural network to predict asset price movement for a one-month horizon. See the how_to_optimize_a_NN_architecure notebook for details.
