# What are classical models?

In this chapter, we'll deal with models that could be characterized as having a longer tradition, and are rooted in statistics and mathematics. They are used heavily in econometrics and statistics.

While there is considerable overlap between statistics and machine learning approaches, and each community has been absorbing the work of the other, there are still a few key differences. Whereas statistics papers are still overwhelmingly formal and deductive, machine learning researchers are more pragmatic, relying on the predictive accuracy of models.

We've talked about the very early history of time-series models in *Chapter 1*, *Introduction to Time-Series with Python*. In this chapter, we'll discuss moving averages and autoregressive approaches for forecasting. These were introduced in the early 20^{th} century and popularized by George Box and Gwilym Jenkins in 1970 in their book "*Time-Series Analysis Forecasting and Control...*