fforms_combinationforecast

Compute combination forecast based on the vote matrix probabilities

A novel meta-learning framework for forecast model selection using time series features. Many applications require a large number of time series to be forecast. Providing better forecasts for these time series is important in decision and policy making. We propose a classification framework which selects forecast models based on features calculated from the time series. We call this framework FFORMS (Feature-based FORecast Model Selection). FFORMS builds a mapping that relates the features of time series to the best forecast model using a random forest. 'seer' package is the implementation of the FFORMS algorithm. For more details see our paper at <https://www.monash.edu/business/econometrics-and-business-statistics/research/publications/ebs/wp06-2018.pdf>.

Thiyanga Talagala

seer

Feature-Based Forecast Model Selection

Rob J Hyndman

George Athanasopoulos

fforms_combinationforecast function

<dl><dt>fforms.ensemble</dt>
<dd>a list output from fforms_ensemble function</dd>
<dt>tslist</dt>
<dd>list of new time series</dd>
<dt>database</dt>
<dd>whethe the time series is from mcom or other</dd>
<dt>h</dt>
<dd>length of the forecast horizon</dd>
<dt>holdout</dt>
<dd>if holdout=TRUE take a holdout sample from your data to caldulate forecast accuracy measure, if FALSE all of the data will be used for forecasting. Default is TRUE</dd>
<dt>parallel</dt>
<dd>If TRUE, multiple cores (or multiple sessions) will be used. This only speeds things up
when there are a large number of time series.</dd>
<dt>multiprocess</dt>
<dd>The function from the <code>future</code> package to use for parallel processing. Either
<code><a href="https://future.futureverse.org/reference/multisession.html">multisession</a></code> or <code><a href="https://future.futureverse.org/reference/multicore.html">multicore</a></code>. The latter is preferred for Linux and MacOS.</dd></dl>

Arguments

Author

Combination forecast based on fforms — fforms_combinationforecast

<dl>

<dt>fforms.ensemble</dt>
<dd>a list output from fforms_ensemble function</dd>


<dt>tslist</dt>
<dd>list of new time series</dd>


<dt>database</dt>
<dd>whethe the time series is from mcom or other</dd>


<dt>h</dt>
<dd>length of the forecast horizon</dd>


<dt>holdout</dt>
<dd>if holdout=TRUE take a holdout sample from your data to caldulate forecast accuracy measure, if FALSE all of the data will be used for forecasting. Default is TRUE</dd>


<dt>parallel</dt>
<dd>If TRUE, multiple cores (or multiple sessions) will be used. This only speeds things up
when there are a large number of time series.</dd>


<dt>multiprocess</dt>
<dd>The function from the <code>future</code> package to use for parallel processing. Either
<code><a href='https://future.futureverse.org/reference/multisession.html'>multisession</a></code> or <code><a href='https://future.futureverse.org/reference/multicore.html'>multicore</a></code>. The latter is preferred for Linux and MacOS.</dd>

</dl>

fforms_combinationforecast: Combination forecast based on fforms

Description

Usage

Value

Arguments

Author