Demand for products/services can be broken down into five components:
- Average demand for the period.
- Seasonal influence.
- Cyclical elements.
- Random variation.
Cyclical factors are more difficult to determine since either the time span or the cause of the cycle may not be known.
Random variations are caused by chance events. When all the known caused for demand are subtracted from the total demand, what remains is the unexplained portion of demand. If you are unable to identify the cause of the remainder, it is just a random chance.
Autocorrelation: denotes the persistance of occurrence. The demand expected at any point is highly correlated with past values.
When demand is random, the demand from one time period to another may vary widely. Where high autocorrelation exists, demand is not expected to change very much from one time period to the next.
Trend lines are the starting point in developing a forecast. Trend lines are then adjusted for expected events that may influence the final forecast.
Linear trend: reflects a straight continuous relationship.
S-curve: typical of a product's growth and maturity cycle. Critical points are where the trend makes a transition from slow growth to fast growth and vice versa.
Asymptotic trend: starts with the highest demand growth at the beginning, which then decreases,
Exponential curve: common in products with explosive growth
Exponential trend: suggests that sales will continue to increase rapidly for some period of time, but which may not last in the long-term.