Wolverine Demand Manager

The Wolverine Demand Manager application provides a role-based, single environment for internal organizations (such as Sales, Marketing, Product Management, Operations and Finance) and external trading partners to collaborate, and make timely, intelligent demand (or sales) forecast decisions that optimize service levels and revenue generation.

Wolverine Demand Manager analyzes all factors that may impact demand such as sales, seasonality, promotions, product lifecycle, etc. and allows users to collaborate from any angle to reach a global consensus demand forecast that is aligned with local objectives.

Wolverine Demand Manager helps companies:

1. Facilitate multiple-user, consensus-based demand planning.
2. Enable multiple-level planning for demand at any level and in any dimension -- from the top down, the middle out, and the bottom up. A set of common business rules can be defined by users to automatically calculate data aggregation and disaggregation.
3. Enable planning in multiple calendar types (daily, weekly, monthly, etc) with automatic calendar conversion. A set of time-based aggregation/disaggregation procedures are provided to automatically synchronize data in different time buckets.
4. Provide a graphical view of sales, forecasts, baseline demand, and promotional uplifts.
5. Forecast demand rather than sales by factoring periods of exceptional demand, causal and promotion events.

Wolverine Demand Manager - Forecasting Engine

The Wolverine Demand Manager Forecasting Engine uses a set of forecast procedures that allows users to choose forecast data of different natures and patterns. The automatic forecasting model setting procedure can automatically select and define the best suited forecasting model and parameters for any given dataset.

The Forecasting Engine also takes the following factors into consideration: relevant product lifecycle profiles, seasonality profiles, and future causal and promotion events. Data cleansing procedures can adjust historical demand variations caused by known (such as promotion events) or unknown factors so to improve the quality of results. Factors include:

Causal Events

• Multiple causal event variables can be easily defined and applied to demand forecast variations caused by non-recurring events, such as competitor activity, etc.
• Events are incorporated into forecasts and take into account abnormal demand caused by these events.

Seasonality Analysis

• Seasonality profiles can be used to analyze seasonal demand patterns. The cycle length can be defined according to the nature of demands.
• The seasonality algorithms can be applied to compute best-fit seasonal factors.
• Seasonal factors can be optionally taken into account by the Forecasting Engine for those items with seasonal demand patterns.

Key Performance Indicators

• Provides a set of common key performance indicators, such as time-lagged forecast errors, various forecast version errors, forecast error variation, etc., to measure the efficiency of forecast planning.
• Key Performance Indicator (KPI) alerts ensure notification when KPIs fall below preset parameters.