This week, you will download $5$ years of daily adjusted closing prices for the Standard & Poor$$s $500$ index from finance.yahoo.com. You will build RNN models with the first $80\%$ of the data and forecast the last $20\%.$ It is important that you split the data in such a way that the withhold set is the last portion of the dataset.

Background Materials

Financial time series is an obvious area for the use of RNN$,$ as the sequence is more important than the individual observations. By building models to forecast indices, you will learn how to employ them in time series modeling.

Management$/$Research Question

In layman$$s terms, what is the management$/$research question of interest, and why would anyone care?

Requirements

Conduct your analysis using the specified $80/20$ split.

Conduct EDA.

Build at least three RNN models based on hyperparameter tuning.

Evaluate goodness of fit metrics.

Discuss your model$$s performance