Making a numerical forecast more accurate by decomposing the figure into a set of separate trends. For example, Collopy and Armstrong (1996) decomposed an apparently random graph of annual highway deaths in the UK into two factors: traffic volume (which was irregularly rising), and death rate (steadily falling).
A method of forecasting where time series data are separated into up to three components: trend, seasonal, and cyclical; where trend includes the general horizontal upward or downward movement over time; seasonal includes a recurring demand pattern such as day of the week, weekly, monthly, or quarterly; and cyclical includes any repeating, non-seasonal pattern. A fourth component is random, that is, data with no pattern. The new forecast is made by projecting the patterns individually determined and then combining them.
(n.) A division of a data structure into substructures that can be distributed separately, or a technique for dividing a computation into subcomputations that can be executed separately. The most common decomposition strategies in parallel computing are: functional decomposition; geometric decomposition and iterative decomposition.