ABSTRACT
In the previous chapter we used the moving averages and exponential smoothing methods in preparing short-term forecasts. Each of the approaches that was used has its advantages and disadvantages. Depending on the nature of the times series data, we suggested a particular methodology. Both the moving average and the exponential models use historical observations to make a forecast. The adaptive filtering approach also depends heavily on historical observations. But in this technique more complicated data patterns such as those with cycles are easily accommodated. In addition, adaptive filtering makes it possible to learn from past errors and correct for it before making a final forecast.
