WHY AUTOBOX IS BETTER THAN "PICK BEST" !

The preset or "pick best" models found in many forecasting systems today produce suboptimal forecasts. To produce more-accurate forecasts, the system needs to automatically tailor the model to the problem at hand, including selecting the best lead and lag structures for each input series and the best weightings. It needs to correct for omitted variables (e.g., holidays or price changes that have affected the historical data, but that the system has no knowledge of) by identifying pulses, seasonal pulses, level shifts and local time trends, and then adding the needed structure through surrogate variables. Conversely, it needs to eliminate unneeded structure (e.g., a statistically unimportant causal variable) to keep the model manageable. It should perform all these functions as part of its normal routine without human intervention.