MSF 599: HOMEWORK 8
The trade_data.csv file contains several fields related to international trade in the U.S. You’re going to need to preprocess the data by (at least) standardizing each column.
1.) Architect a neural network like the one in the figure below that uses the Keras library classes to predict the change (up or down) in GDP (column B) the following year. Of course, there are more than 4 inputs in the trade_data.csv data set.
2.) Architect a neural network like the one in the figure below that uses the data to predict the category of the following year’s log return on the S&P 500 where the categories are down more than one standard deviation, between minus one and plus one standard deviation, and up more than one standard deviation.