Forecasting#
Note
The user guide is under development. We have created a basic structure and are looking for contributions to develop the user guide further. For more details, please go to issue #361 on GitHub.
Introduction#
Forecasating is making forward temporal predictions based on past data. The simplest case is the univariate case.
Inputs.
Univariate time series, \(y = y(0), y(1), y(2), ..., y(N)\)
Forecasting horizon, \(fh = N+1, N+2, ..., N+h\)
Output.
Predictions of \(y\) at the times in \(fh\), \(\hat{y} = \hat{y}(N+1), \hat{y}(N+2), ..., \hat{y}(N+h)\)
Examples.
Forecasting the global population
Forecasting the price of a stock
Forecasting the daily maximum temperature in a given location
Example#
Predicting flights. See the Tutorial on Forecasting.
Algorithms included in sktime#
See the API Reference.