This page enables you to identify the basic linear trend and seasonability in ‌historic demand. Decomposition pulls out predicted mean, trend, and seasonality to understand variability. You must understand seasonality and trend to identify variability/randomness.

Before you start

Use the context selectors at the top-right to select a product and combination. Additionally, you can manually enter the required values using the search function.

Use the Customer Filter and Product Filter fields to filter on a specific customer and product.

History Validation

The History Validation card indicates if there is enough history to perform a decomposition analysis.

Selected History and Seasonal Index

The Year on Year Selected History and Seasonal Index chart provides a yearly comparison of the chained history (demand history). You can hover over the legend to view specific yearly views across a 52-week period. This helps you to review seasonality patterns of demand. 

The selected history displays the period from which the application can determine seasonality. It displays the Effective Adjusted History overlaid with Seasonality Initialization Range for each financial year (CFY: Current Financial Year) to provide a year-on-year view of demand.

The Seasonal Indices measure how a season throughout a cycle compares to the average season.

Note: A minimum of 24 months history is required to detect seasonal trend.

History, Trend, and Residual

The chart shows:

ParameterValue
Residual (U)

It represents what's left in a time series model after fitting a model. For many time series models, residuals are the difference between the data and the values that are fitted.

Residuals are useful in checking whether a model has adequately captured the information in the data. A good forecasting method yields residuals with the properties below:

  • Uncorrelated residuals: If there are correlations between residuals, there's information left in the residuals that should be used in computing forecasts.
  • Residuals have zero mean: If the residuals have a mean other than zero, the forecasts are biased.
Chained History (U)It represents the Effective Adjusted History overlaid with Seasonality Initialization Range.
Trend (U)

Displays the mean of the Trendline. 

A trend is the general direction of change in a variable over time. Trends can be upward, downward, or flat, and are usually associated with structural causes.

Trend (U) *SeasonalityIt represents history trend, including the seasonality index.