What is Time
Time series forecasting methods produce forecasts based solely on historical
values. Time series forecasting methods are widely used in business situations where
forecasts of a year or less are required. The time series techniques used in
ezForecaster are particularly suited to Sales, Marketing, Finance, and Production
planning. Time series methods have the advantage of relative simplicity, but certain
factors need to be considered:
Time series methods are better suited to short-term forecasts
(i.e., less than a year).
Time series forecasting relies on sufficient past data being
available and that the data is of a high quality and truly representative.
Time series methods are best suited to relatively stable
situations. Where substantial fluctuations are common and underlying conditions are
subject to extreme change, then time series methods may give relatively poor results.
Classically, researchers approach the problem of modeling a time series by
identifying four kinds of change. These four components are known as the Trend,
Fluctuation, Seasonality and Residual Effect.
The Trend is the increase or decrease in the series over a long
period of time. For this reason is also known as the long-term trend.
The Cyclical Fluctuation or (Cyclicity) is the wavelike up and down
fluctuations about the trend that is attributable to economic or business conditions. This
fluctuation is also known as business cycle. During economic expansion, the cycle lies
above the trend; during a downturn, beneath it.
The Seasonality or (Seasonal Variation) in a time series is the fluctuation that
occurs each month, each year etc. Seasonal variations tend to be repeated from year to
Lastly, the Residual Effect is what remains, having removed the
Trend, Cyclical and Seasonal components of a time series. It represents the random error
effect of a time series, caused by events as widespread as wars, hurricanes, strikes and
randomness of human actions.
Forecasting is not an exact science. Often the four components are
difficult to discern. For this reason, ezForecaster offers a variety of
forecasting techniques, ranging from simple methods through
sophisticated state-of-the-art techniques.