Visualize PlanIQ results including forecasts, seasonality, and trend components.
Before you start
Use the context selectors in the top right to select a PlanIQ method, product, and customer.
PlanIQ algorithms produce a distribution of possible values, rather than a single-point forecast. This distribution can be divided into quantiles. In forecasts, quantiles help address forecasted value doubt by defining a prediction interval, within which the actual value is likely to fall with a given probability (P).
Use the graphs on the page to visualize PlanIQ results.
| Graph | Description |
| PlanIQ Forecast | Displays weekly PlanIQ historical data and three forecast scenarios values. |
| Item Level Explanability | Displays the explanability of items. |
| Seasonality | Displays repeating patterns of higher and lower values over weekly, bi-weekly, monthly, quarterly, and yearly periods. |
| Trend | Displays the a overall pattern of the data over over quarterly and yearly periods. |
Additional information
PlanIQ quantile example
- A P10 quantile indicates that the true observed value is expected to be lower than the forecasted value 10% of the time. P10 is a probability of 10%.
- A P90 quantile indicates that the true value is expected to be lower than the forecasted value 90% of the time. The difference between the P10 and P90 defines an interval range of 80%.
- This means that the probability that the true value falls between the forecasted values for the P10 and P90 quantiles is 80%. Increasing the difference between the quantiles will increase the interval range and the probability.
For the median, or P50, 50% of the distribution falls on either side of the cut point. For quartiles, 25% of the distribution is in each interval at P25, P50, and P75.
See the Quantiles PlanIQ page for more detail.
