Summary
In this chapter, we have investigated the use of autoregression models, which predict future values based on the temporal behavior of prior data in the series. Using autoregression modeling, we were able to accurately model the closing price of the S&P 500 over the years 1986 to 2018 and a year into the future. On the other hand, the performance of autoregression modeling to predict annually periodic temperature data for Austin, Texas, seemed more limited.
Now that we have experience with regression problems, we will turn our attention to classification problems in the next chapter.