Problem 1: The Hughes Supply Company uses an inventory management system that requires monthly forecasts of each item for the next four months. The data file provided includes demand data for one electrical fixture for the past 24 months. a. Produce a time-series plot of the data and describe any predictable dynamics that you see in the plot. b. Fit a four-period moving average and an exponential smoothing model with a= 0:30 over the training sample, and evaluate your models based on their performance over a holdout sample of appropriate length. Which of your two models would you recommend and why? [Use a three-period centered average to initialize your exponential smoothing model.] c. For whichever model you recommended in Part B, use that model to produce a point forecast and prediction interval for demand in each of the next four months in the future.

Problem 2: AmeriPlas produces 20-ounce plastic drinking cups that are embossed with the names of prominent beers and soft drinks. It has been observed that demand for the cups has exhibited a positive trend over time. The data le provided includes the demand data by month for 2014 through 2017. a. Fit a Holt model with (a; b ) = (0:30; 0:20) and another with (a; b) = (0:25; 0:15). Initialize both models using the first six data points. Evaluate your models on the basis of their performance over a four-month holdout sample. Which of your two models would you recommend and why? b. For whichever model you recommended in Part A, use that model to produce a point forecast and prediction interval for demand in each of the next four months in the future.