Chapter 11: Additional Statistical Modeling Techniques for Time Series
In Chapter 10, Building Univariate Time Series Models Using Statistical Methods, you were introduced to exponential smoothing, non-seasonal ARIMA, and seasonal ARIMA for building forecasting models. These are popular techniques and are referred to as classical or statistical forecasting methods. They are fast, simple to implement, and easy to interpret.
In this chapter, you will dive head-first and learn about additional statistical methods that build on the foundation you gained from the previous chapter. This chapter will introduce a few libraries that can automate time series forecasting and model optimization—for example, auto_arima and Facebook's Prophet library. Additionally, you will explore statsmodels' vector autoregressive (VAR) class for working with multivariate time series and the arch library, which supports GARCH for modeling volatility in financial data.
The main goal of this...
