The Predictive Model Components
Get to know how Smart Predictdecomposes the signal.
A Time Series Forecasting predictive model can contain the following components:
| Components | Information |
|---|---|
| Trend | The Trend is the general orientation of the signal. A Trend pattern exists when there is a long-term increase or decrease in the data. It does not have to be linear. It can change direction, for example, increasing then decreasing. |
| Cycle | A Cycle pattern exists when a series is influenced by cyclic factors (for example: the quarter, the month, the day of the week). The cycle is always of a fixed and known period. |
| Fluctuation | A Fluctuation pattern exists when data exhibits rises and falls
that are not of fixed periods. It indicates dependency of the values
at time T with previous values (dependence of observations) in the
case of an autoregressive component. For example, the predictive model can detect that the previous 37 values have an impact on the actual values. |
Note
If you have choosen to get predictive forecasts per entity, you have this information for
each entity.