b) Forecast the revenue for January of Year 5 using the exponential smoothing method. Consider three different smoothing constants for the calculations: 0.3, 0.5, and 0.7. (Note: forecast for January year 1 is equal to January year 1 actual value) (12 marks)
1. Do forecasts for January Year 5 change if you change the smoothing constant values in your calculations? Enumerate the three different forecasts for January Year 5. (2 marks)
2. Plot both the actual revenue and the predicted revenues for all the three calculations (You will have four plots in total on one chart). (2 marks)
3. Visually inspect the plots for all three predictions (i.e. predictions based on smoothing constant values of 0.3, 0.5, and 0.7).
(i) What are the advantages of using a small value for the smoothing constant? What are the disadvantages? (2 marks)
(ii) What are the advantages of using a large value for the smoothing constant? What are the disadvantages? (2 marks)
4. Which model is the best (the one based on alpha 0.3, 0.5, or 0.7)? Why? Show your calculations. (4 marks)
c) Using the decomposition method, forecast revenues for each month of Year 5. (20 marks)
d) Using multiple regression analysis, forecast revenues for each month of Year 5 (16 marks)
e) Compare the models, the best models from a and b, and the models based on regression analysis and the decomposition method and choose the best one. Which model is the best? Why? Show your calculations. (10 marks)