Business Forecasting 101
Common terms and definitions for forecasting optimization
Vanguard has cataloged a small library of notes and definitions of various forecast methods and common issues, including advice and best practices for applying analytic prudence to your data. Check back for new topics and webinar notifications, or Join the Vanguard LinkedIn User Group for tips from peers and alerts on new topics and events.
Business Forecasting 101 : 01
- Demand management
- Demand forecasting
- Business forecasting
- Inventory planning
- Statistical forecasting
- Time series forecasting
Forecasting is a decision-making tool used by many businesses to help in budgeting, planning, and estimating future growth. In the simplest terms, forecasting is the attempt to predict future outcomes based on past events and management insight.
Business Forecasting 101: 02
- Forecasting methods, models, techniques
- Moving averages
- Exponential smoothing
- Regression analysis models
- Hybrid forecasting methods
- Decomposition forecasting methods
- Spectral analysis
- Custom forecasting models
The forecasting method you select is a function of multiple qualities about your item. Is demand steady, cyclical or sporadic? Are there seasonal trends? Are trends strong or limited? Each item being forecast has a somewhat unique history (and future), and therefore an optimal method.
Business Forecasting 101: 03
- Residual analysis
- Determining forecast fit
- Out of sample testing/ holdout sample
- Straight line forecast myth
- Forecast error
- Symmetric mean absolute percent error (SMAPE)
- Mean absolute percent error (MAPE)
- Last absolute deviation z-score
- Mean absolute deviation (MAD), mean absolute error (MAE)
- Mean absolute deviation percent (MADP)
Forecast fit refers to how successfully your chosen forecast method fits to your actuals. A forecast is considered a good fit if it captures all patterns and trends, but ignores random noise.
Business Forecasting 101: 04
- Spare parts forecasting
- New product forecasting
- Using comparables for forecasting
Difficult forecasting requires multiple forecasting methods and analysis be applied to determine which is best for a given scenario. Methods include examples such as: comparable forecasting, spread curve, supersession, and adoption modeling.