Consider using a simple moving average model. Experiment with models using five weeks' $(5-$MA$)$ and three weeks' $(3-$MA$)$ past data. The past $($historical$)$ data in each region are given below $($week $1$ is the week before week $1$ in the table, $2$ is two weeks before week $1,$ etc.$).$ Evaluate the forecasts that would have been made over the $13$ weeks using the overall $($at the end of the $13$ weeks$).$ Use mean absolute deviation $($MAD$),$ as a criterion.

Next, consider using a simple exponential smoothing model. In your analysis, test two alpha values, $\mathrm{.}2$ and $\mathrm{.}4.$ Use the MAD for evaluating the model. When using an alpha value of $\mathrm{.}2,$ assume that the forecast for week $1$ is the past three$-$week average $($the average demand for periods $-3,-2,$ and $-1).$ For the model using an alpha of $\mathrm{.}4,$ assume that the forecast for week $1$ is the past five$-$week average.

Starbucks is considering simplifying the supply chain for their coffeemaker. Instead of stocking the coffeemaker in all five distribution centers, they are considering only supplying it from a single location. Evaluate this option by analyzing how accurate the forecast would be based on the demand aggregated across all regions. Use the model that you think is best from your analysis of parts $1$ and $2.$ When using an alpha value of $\mathrm{.}2,$ assume that the forecast for week $1$ is the past three$-$week average $($the average demand for periods $-3,-2,$ and $-1).$ For the model using an alpha of $\mathrm{.}4,$ assume that the forecast for week $1$ is the past five$-$week average. Evaluate your new forecast using MAD.

What are the advantages and disadvantages of aggregating demand from a forecasting view? Are there other things that should be considered when going from multiple distribution centers to a single distribution center?