ABC Global Coffee (AGC), originally from Seoul, South Korea, manages a huge supply chain that includes 5,000 stores around the Asia region. Although the store's appearance seems to be similar, their specific operations are different based on the city. Depending on the specific location of the store, its concept (i.e., store size), and targeting such regional customers, AGC sets various operational strategies.

AGCs' products are distributed through five distribution centers in Asia. For example, an ACG original roasted coffee bean, sold at retail stores (e.g., department store). The coffee has been a steady seller and does not consider this as a seasonal item, but there exists some demand variability in demand. Demand for coffee over the past 12 weeks is shown in the following table. The demand at the distribution centers (DCs) varies between about 38 units on average per week in Seoul and 48 units in Shang-hi. The current quarter's data are pretty close to the demand shown in the table. The management team would like you to experiment with some forecasting models to determine what should be used in a new system to be implemented.

The new system is programmed to use one of two forecasting models: simple moving average and exponential smoothing

Q1. Consider using a simple moving average model. Experiment with models using five weeks’ and three weeks’ past data. The past data in each region are given below (week -1 is the week before week1, week -2 two weeks before week 1, etc). Evaluate the forecasts that would have been made over the 12 weeks using the overall (at the end of 12 weeks) mean absolute deviation, mean absolute percentage error, and tracking signal as criteria. Additionally, let’s consider exponential smoothing. In your analysis, test two alpha values, 0.2 and 0.4. Use the same criteria for evaluating the model as in previous question. When using an alpha value 0.2, 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 0.4, assume that the forecast for week 1 is the average of the past five-week.

Q2. Now, AGC is considering simplifying the supply chain for its coffee. Instead of stocking the coffee in all five distribution centers, it is 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 the previous two questions. Evaluate your new forecast using mean absolute deviation, mean absolute percent error, and the tracking signal

Q3. 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 DCs to one DC? Please describe.

Week 2 3 Seoul 33 45 37 Hong Kong 26 35 41 Shang-hi 44 34 22 Tokyo 27 42 35 Singapore 32 43 54 Total 162 199 189 4 38 40 55 40 40 213 5 30 48 72 64 74 288 6 18 55 62 70 40 245 7 58 18 28 65 35 204 8 47 62 27 55 45 236 12 Average 40 38 50 41 47 48 42 47 50 43 261 229 220 9 10 37 23 44 30 95 35 58 43 38 47 38 48 56 257 174 11 545