Forecasting is the practice of analyzing historical data to predict anticipated conditions in the future and is at the core of supply chains. Naturally, increasing their accuracy became highly sought after. But what factors affect forecasting accuracy?

Perhaps surprisingly is the discovery that the forecasting method used has little effect on the quality of the forecast produced. On the contrary, the time horizon of the forecast and the level of data aggregation and variability has a direct impact on accuracy.

The longer the period over which the forecast is made, the less accurate it is likely to be. For example, a forecast for next week will almost always be more accurate than a forecast for the next month or year. When it comes to data, a relatively stable demand data will output very accurate forecasts compared to data points with a high degree of variability. Owing to this, comparisons of forecasts only hold any significance when they have the same timeframe and are based on historical data exhibiting similar levels of stability.