Exercise

# Unrolling ARMA forecast

Now you will use the model that you trained in the previous exercise `arma`

in order to forecast the absolute value of the Amazon stocks dataset. Remember that sometimes predicting the difference could be enough; will the stocks go up, or down; but sometimes the absolute value is key.

The results object from the model you trained in the last exercise is available in your environment as `arma_results`

. The `np.cumsum()`

function and the original DataFrame `amazon`

are also available.

Instructions

**100 XP**

- Use the
`.get_forecast()`

method of the`arma_results`

object and select the predicted mean of the next 10 differences. - Use the
`np.cumsum()`

function to integrate your difference forecast. - Add the last value of the original DataFrame to make your forecast an absolute value.