Forecast Level Optimization

Traditional Forecast engines forecast at the level defined by the Demand Planner, then disaggregate and store the resulting forecasts at the base level (e.g., Week | Product ID | Customer ID).

Forecast Level Optimization enables vyan.ai to evaluate Forecastability at all higher levels in all regular Dimensions.

For example, Product Dimension may have the following attributes within it:

• Product ID

• Product Group

• Product Family

• Business Unit

Similarly, Customer Dimension may have the following attributes within it:

• Customer ID

• Customer Group

• Customer Region

In this case, vyan.ai will automatically generate Forecasts at all aggregated levels per list below:

• Week | Product ID | Customer Group

• Week | Product ID | Customer Region

• Week | Product Group | Customer ID

• Week | Product Group | Customer Group

• Week | Product Group | Customer Region

• Week | Product Family | Customer ID

• Week | Product Family | Customer Group

• Week | Product Family | Customer Region

• Week | Business Unit | Customer ID

• Week | Business Unit | Customer Group

• Week | Business Unit | Customer Region

vyan.ai generates disaggregation factors to split such aggregated forecasts down to the Base Level: Week | Product ID | Customer ID. This is needed to ensure apples-to-apples comparison of all forecasts in terms of forecast error.

This enables vyan.ai to understand which levels of aggregation enable better forecastability.

vyan.ai Optimal Blending process then allocated optimal weights to all such competing forecasts from all levels (and across all forecast models).