Forecasting with Information from the Future

Abstract

This chapter describes the method we use to predict the demand for a new brand over its entire future life cycle before the brand is introduced into the market. The forecast is a prior forecast prepared at time t−1 using all the data that is available up till time t−1. Additional information about the future in the form of advance orders becomes available at time t. The advance orders contain the customers' plans for future purchases. They contain therefore a forecast for future demand. This chapter discusses how at time t−1 the prior forecast of, and the estimate of the locus of, a new brand's life cycle (based on information up to t−1) for the future periods t+1, t+2, …,t+k are developed. The chapter discusses how at time t when advance orders become available for the future periods t+1, t+2, …,t+k the prior forecast is updated for the length of the life cycle with this new information. These updates are made using Kalman's filter. Using this method we have been able to obtain good estimates of the locus of the life cycle of new brands. We have also been able to predict the turning points in the brand's life cycle six months before it occurs. The chapter shows a method for developing sequentially improved forecasts.

Citation

Waage, F. (2011), "Forecasting with Information from the Future", Lawrence, K.D. and Klimberg, R.K. (Ed.) Advances in Business and Management Forecasting (Advances in Business and Management Forecasting, Vol. 8), Emerald Group Publishing Limited, Leeds, pp. 155-167. https://doi.org/10.1108/S1477-4070(2011)0000008013