Engine Tuning is the term used for improving the results of the Demantra Statistical Engine and involves the analysis of engine models, the forecast tree and parameter settings.
Data segmentation, seasonality, sales and marketing bias, number of (and accuracy of) overrides, forecast horizons, proportionality, product lifecycle, events and promotions, resource skill and availability... These are key factors to determine where resources (engine, planners & managers) should focus their tuning efforts to maximise volume, value, margin and time.
Forecast tuning will result in an improved statistical forecast and will provide you with deeper understanding of your data and can then drive planning strategy.
The key Engine Tuning elements can be summarised thus:
- Demand Data Profiles (history)
- Node Processing (forecast decision and generation process)
- Forecast Tree (hierarchy levels used by engine)
- Engine Profiles (statistical engine model settings)
- Engine Parameters (methodology settings)
- Causals / Promotions (history and future effects)
- Proport Function (allocation & aggregation)
- Nodal Tuning (Settings per combination)
- Procedures (methodology and approach to tuning)
We can perform engine tuning on your behalf or train resources to become skilled in the science and art of creating improved forecasts. Engine Tuning can only be properly undertaken with access to all the administrative components of Demantra and preferably a dedicated Tuning environment.