Home / Model library / Univariate, time series models
Model library · Univariate, time series modelsA simple model using the last value as a prediction for the future.
The naive model is very basic, and used as a benchmark for the other models. It simply works by taking the last historic value and using it as the forecast. Mathematically the forecast point of the series Yt can be written as
where εt is the error term which is not explained by the model.
Indicio tests this model on your history next to 80+ others, at every horizon, and keeps the ones that forecast best. With leading indicators chosen for you from over 400 million series, and every number explained.
An autoregressive integrated moving average (ARIMA) model is a generalization of an autoregressive moving average (ARMA)…
Read moreETSExponential smoothing is a rule of thumb technique for smoothing time series data using the exponential window…
Read moreNeural NetAn artificial neural network (ANN) is a model which is based on a collection of connected units or nodes called artificial…
Read moreProphetProphet is a procedure for forecasting time series data based on an additive model where non-linear trends are fit with yearly,…
Read moreSTLSTL is a versatile and robust method for decomposing time series. STL is an acronym for “Seasonal and Trend decomposition using…
Read moreTBATSTBATS is a time series model that is useful for handling data with multiple seasonal patterns. TBATS is an acronym for key…
Read more