FORAMonthForecast: Monthly M3-Competition forecasts

In svcuonghvktqs/FORA: A package for time sereis forecast accuracy evaluation

Description

The monthly forecasts of yearly time series from all the original participating methods in the M3 forecasting competition.

Usage

FORAMonthForecast

Format

FORAMonthForecast is a data frame of the result of all the original participating methods in the M3 forecasting competition with the following structure:

series_id

Time series identifier - aunique name that identifies a time series

category

The type of series. Possible values for M3 are "DEMOGRAPHIC", "FINANCE", "INDUSTRY", "MACRO", "MICRO", "OTHER".

actual

The value observed

method

Method identifier - a unique name that identifies a method by which the forecasting result was calculated.

forecast

Forecast from all the original participating methods in the M3 forecasting competition.

horizon

Forecast horizon

timestamp

Any representation of the period to which the observation relates.

Author(s)

Sai Van Cuong, Andrey Davydenko, Maxim Shcherbakov

Source

http://forecasters.org/resources/time-series-data/m3-competition/.

References

Makridakis and Hibon (2000) The M3-competition: results, conclusions and implications. International Journal of Forecasting, 16, 451-476.

See Also

FORAQuartForecast, FORAYearForecast

Examples

FORAMonthForecast
subset(FORAMonthForecast, series_id == "M1")

svcuonghvktqs/FORA documentation built on May 20, 2019, 9:57 a.m.